* [PATCH 3/4] generic block based fiemap implementation
@ 2008-06-25 22:19 Mark Fasheh
0 siblings, 0 replies; 13+ messages in thread
From: Mark Fasheh @ 2008-06-25 22:19 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Josef Bacik
From: Josef Bacik <jbacik@redhat.com>
Any block based fs (this patch includes ext3) just has to declare its own
fiemap() function and then call this generic function with its own
get_block_t. This works well for block based filesystems that will map
multiple contiguous blocks at one time, but will work for filesystems that
only map one block at a time, you will just end up with an "extent" for each
block. One gotcha is this will not play nicely where there is hole+data
after the EOF. This function will assume its hit the end of the data as soon
as it hits a hole after the EOF, so if there is any data past that it will
not pick that up. AFAIK no block based fs does this anyway, but its in the
comments of the function anyway just in case.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
fs/ext2/ext2.h | 2 +
fs/ext2/file.c | 1 +
fs/ext2/inode.c | 8 +++
fs/ext3/file.c | 1 +
fs/ext3/inode.c | 8 +++
fs/ioctl.c | 119 +++++++++++++++++++++++++++++++++++++++++++++++
include/linux/ext3_fs.h | 2 +
include/linux/fs.h | 3 +
8 files changed, 144 insertions(+), 0 deletions(-)
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 47d88da..bae998c 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -133,6 +133,8 @@ extern void ext2_truncate (struct inode *);
extern int ext2_setattr (struct dentry *, struct iattr *);
extern void ext2_set_inode_flags(struct inode *inode);
extern void ext2_get_inode_flags(struct ext2_inode_info *);
+extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len);
int __ext2_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata);
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 5f2fa9c..45ed071 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -86,4 +86,5 @@ const struct inode_operations ext2_file_inode_operations = {
#endif
.setattr = ext2_setattr,
.permission = ext2_permission,
+ .fiemap = ext2_fiemap,
};
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 384fc0d..f3b9d12 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -31,6 +31,7 @@
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
+#include <linux/fiemap.h>
#include "ext2.h"
#include "acl.h"
#include "xip.h"
@@ -704,6 +705,13 @@ int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_
}
+int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ return generic_block_fiemap(inode, fieinfo, start, len,
+ ext2_get_block);
+}
+
static int ext2_writepage(struct page *page, struct writeback_control *wbc)
{
return block_write_full_page(page, ext2_get_block, wbc);
diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index acc4913..3be1e06 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -134,5 +134,6 @@ const struct inode_operations ext3_file_inode_operations = {
.removexattr = generic_removexattr,
#endif
.permission = ext3_permission,
+ .fiemap = ext3_fiemap,
};
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 6ae4ecf..878b6da 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -36,6 +36,7 @@
#include <linux/mpage.h>
#include <linux/uio.h>
#include <linux/bio.h>
+#include <linux/fiemap.h>
#include "xattr.h"
#include "acl.h"
@@ -981,6 +982,13 @@ out:
return ret;
}
+int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ return generic_block_fiemap(inode, fieinfo, start, len,
+ ext3_get_block);
+}
+
/*
* `handle' can be NULL if create is zero
*/
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 0db1f8d..2c07e4b 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -13,6 +13,8 @@
#include <linux/security.h>
#include <linux/module.h>
#include <linux/uaccess.h>
+#include <linux/writeback.h>
+#include <linux/buffer_head.h>
#include <asm/ioctls.h>
@@ -227,6 +229,123 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg)
return error;
}
+#define blk_to_logical(inode, blk) (blk << (inode)->i_blkbits)
+#define logical_to_blk(inode, offset) (offset >> (inode)->i_blkbits);
+
+/*
+ * @inode - the inode to map
+ * @arg - the pointer to userspace where we copy everything to
+ * @get_block - the fs's get_block function
+ *
+ * This does FIEMAP for block based inodes. Basically it will just loop
+ * through get_block until we hit the number of extents we want to map, or we
+ * go past the end of the file and hit a hole.
+ *
+ * If it is possible to have data blocks beyond a hole past @inode->i_size, then
+ * please do not use this function, it will stop at the first unmapped block
+ * beyond i_size
+ */
+int generic_block_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo, u64 start,
+ u64 len, get_block_t *get_block)
+{
+ struct buffer_head tmp;
+ unsigned int start_blk;
+ long long length = 0, map_len = 0;
+ u64 logical = 0, phys = 0, size = 0;
+ u32 flags = FIEMAP_EXTENT_MERGED;
+ int ret = 0;
+ dev_t dev = inode->i_sb->s_dev;
+
+ if ((ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC)))
+ return ret;
+
+ start_blk = logical_to_blk(inode, start);
+
+ /* guard against change */
+ mutex_lock(&inode->i_mutex);
+
+ length = (long long)min_t(u64, len, i_size_read(inode));
+ map_len = length;
+
+ do {
+ /*
+ * we set b_size to the total size we want so it will map as
+ * many contiguous blocks as possible at once
+ */
+ memset(&tmp, 0, sizeof(struct buffer_head));
+ tmp.b_size = map_len;
+
+ ret = get_block(inode, start_blk, &tmp, 0);
+ if (ret)
+ break;
+
+ /* HOLE */
+ if (!buffer_mapped(&tmp)) {
+ /*
+ * first hole after going past the EOF, this is our
+ * last extent
+ */
+ if (length <= 0) {
+ flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size,
+ flags, dev);
+ break;
+ }
+
+ length -= blk_to_logical(inode, 1);
+
+ /* if we have holes up to/past EOF then we're done */
+ if (length <= 0)
+ break;
+
+ start_blk++;
+ } else {
+ if (length <= 0 && size) {
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size,
+ flags, dev);
+ if (ret)
+ break;
+ }
+
+ logical = blk_to_logical(inode, start_blk);
+ phys = blk_to_logical(inode, tmp.b_blocknr);
+ size = tmp.b_size;
+ flags = FIEMAP_EXTENT_MERGED;
+
+ length -= tmp.b_size;
+ start_blk += logical_to_blk(inode, size);
+
+ /*
+ * if we are past the EOF we need to loop again to see
+ * if there is a hole so we can mark this extent as the
+ * last one, and if not keep mapping things until we
+ * find a hole, or we run out of slots in the extent
+ * array
+ */
+ if (length <= 0)
+ continue;
+
+ ret = fiemap_fill_next_extent(fieinfo, logical, phys,
+ size, flags, dev);
+ if (ret)
+ break;
+ }
+ cond_resched();
+ } while (1);
+
+ mutex_unlock(&inode->i_mutex);
+
+ /* if ret is 1 then we just hit the end of the extent array */
+ if (ret == 1)
+ ret = 0;
+
+ return ret;
+}
+EXPORT_SYMBOL(generic_block_fiemap);
+
static int file_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
{
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 36c5403..2dc0dbb 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -836,6 +836,8 @@ extern void ext3_truncate (struct inode *);
extern void ext3_set_inode_flags(struct inode *);
extern void ext3_get_inode_flags(struct ext3_inode_info *);
extern void ext3_set_aops(struct inode *inode);
+extern int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len);
/* ioctl.c */
extern int ext3_ioctl (struct inode *, struct file *, unsigned int,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2069bfc..27e7245 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1978,6 +1978,9 @@ extern int vfs_fstat(unsigned int, struct kstat *);
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
unsigned long arg);
+extern int generic_block_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo, u64 start,
+ u64 len, get_block_t *get_block);
extern void get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
--
1.5.4.1
^ permalink raw reply related [flat|nested] 13+ messages in thread
* [PATCH 3/4] generic block based fiemap implementation
2008-09-13 18:49 ` [PATCH 2/4] ocfs2: fiemap support Theodore Ts'o
@ 2008-09-13 18:49 ` Theodore Ts'o
0 siblings, 0 replies; 13+ messages in thread
From: Theodore Ts'o @ 2008-09-13 18:49 UTC (permalink / raw)
To: linux-fsdevel; +Cc: linux-ext4, akpm, Josef Bacik, Mark Fasheh
From: Josef Bacik <jbacik@redhat.com>
Any block based fs (this patch includes ext3) just has to declare its own
fiemap() function and then call this generic function with its own
get_block_t. This works well for block based filesystems that will map
multiple contiguous blocks at one time, but will work for filesystems that
only map one block at a time, you will just end up with an "extent" for each
block. One gotcha is this will not play nicely where there is hole+data
after the EOF. This function will assume its hit the end of the data as soon
as it hits a hole after the EOF, so if there is any data past that it will
not pick that up. AFAIK no block based fs does this anyway, but its in the
comments of the function anyway just in case.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
fs/ext2/ext2.h | 2 +
fs/ext2/file.c | 1 +
fs/ext2/inode.c | 8 +++
fs/ext3/file.c | 1 +
fs/ext3/inode.c | 8 +++
fs/ioctl.c | 118 +++++++++++++++++++++++++++++++++++++++++++++++
include/linux/ext3_fs.h | 2 +
include/linux/fs.h | 3 +
8 files changed, 143 insertions(+), 0 deletions(-)
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 47d88da..bae998c 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -133,6 +133,8 @@ extern void ext2_truncate (struct inode *);
extern int ext2_setattr (struct dentry *, struct iattr *);
extern void ext2_set_inode_flags(struct inode *inode);
extern void ext2_get_inode_flags(struct ext2_inode_info *);
+extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len);
int __ext2_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata);
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 5f2fa9c..45ed071 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -86,4 +86,5 @@ const struct inode_operations ext2_file_inode_operations = {
#endif
.setattr = ext2_setattr,
.permission = ext2_permission,
+ .fiemap = ext2_fiemap,
};
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 991d6df..7658b33 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -31,6 +31,7 @@
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
+#include <linux/fiemap.h>
#include "ext2.h"
#include "acl.h"
#include "xip.h"
@@ -704,6 +705,13 @@ int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_
}
+int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ return generic_block_fiemap(inode, fieinfo, start, len,
+ ext2_get_block);
+}
+
static int ext2_writepage(struct page *page, struct writeback_control *wbc)
{
return block_write_full_page(page, ext2_get_block, wbc);
diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index acc4913..3be1e06 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -134,5 +134,6 @@ const struct inode_operations ext3_file_inode_operations = {
.removexattr = generic_removexattr,
#endif
.permission = ext3_permission,
+ .fiemap = ext3_fiemap,
};
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 507d868..ebfec4d 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -36,6 +36,7 @@
#include <linux/mpage.h>
#include <linux/uio.h>
#include <linux/bio.h>
+#include <linux/fiemap.h>
#include "xattr.h"
#include "acl.h"
@@ -981,6 +982,13 @@ out:
return ret;
}
+int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ return generic_block_fiemap(inode, fieinfo, start, len,
+ ext3_get_block);
+}
+
/*
* `handle' can be NULL if create is zero
*/
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 274625a..682c252 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -13,6 +13,8 @@
#include <linux/security.h>
#include <linux/module.h>
#include <linux/uaccess.h>
+#include <linux/writeback.h>
+#include <linux/buffer_head.h>
#include <asm/ioctls.h>
@@ -223,6 +225,122 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg)
return error;
}
+#define blk_to_logical(inode, blk) (blk << (inode)->i_blkbits)
+#define logical_to_blk(inode, offset) (offset >> (inode)->i_blkbits);
+
+/*
+ * @inode - the inode to map
+ * @arg - the pointer to userspace where we copy everything to
+ * @get_block - the fs's get_block function
+ *
+ * This does FIEMAP for block based inodes. Basically it will just loop
+ * through get_block until we hit the number of extents we want to map, or we
+ * go past the end of the file and hit a hole.
+ *
+ * If it is possible to have data blocks beyond a hole past @inode->i_size, then
+ * please do not use this function, it will stop at the first unmapped block
+ * beyond i_size
+ */
+int generic_block_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo, u64 start,
+ u64 len, get_block_t *get_block)
+{
+ struct buffer_head tmp;
+ unsigned int start_blk;
+ long long length = 0, map_len = 0;
+ u64 logical = 0, phys = 0, size = 0;
+ u32 flags = FIEMAP_EXTENT_MERGED;
+ int ret = 0;
+
+ if ((ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC)))
+ return ret;
+
+ start_blk = logical_to_blk(inode, start);
+
+ /* guard against change */
+ mutex_lock(&inode->i_mutex);
+
+ length = (long long)min_t(u64, len, i_size_read(inode));
+ map_len = length;
+
+ do {
+ /*
+ * we set b_size to the total size we want so it will map as
+ * many contiguous blocks as possible at once
+ */
+ memset(&tmp, 0, sizeof(struct buffer_head));
+ tmp.b_size = map_len;
+
+ ret = get_block(inode, start_blk, &tmp, 0);
+ if (ret)
+ break;
+
+ /* HOLE */
+ if (!buffer_mapped(&tmp)) {
+ /*
+ * first hole after going past the EOF, this is our
+ * last extent
+ */
+ if (length <= 0) {
+ flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size,
+ flags);
+ break;
+ }
+
+ length -= blk_to_logical(inode, 1);
+
+ /* if we have holes up to/past EOF then we're done */
+ if (length <= 0)
+ break;
+
+ start_blk++;
+ } else {
+ if (length <= 0 && size) {
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size,
+ flags);
+ if (ret)
+ break;
+ }
+
+ logical = blk_to_logical(inode, start_blk);
+ phys = blk_to_logical(inode, tmp.b_blocknr);
+ size = tmp.b_size;
+ flags = FIEMAP_EXTENT_MERGED;
+
+ length -= tmp.b_size;
+ start_blk += logical_to_blk(inode, size);
+
+ /*
+ * if we are past the EOF we need to loop again to see
+ * if there is a hole so we can mark this extent as the
+ * last one, and if not keep mapping things until we
+ * find a hole, or we run out of slots in the extent
+ * array
+ */
+ if (length <= 0)
+ continue;
+
+ ret = fiemap_fill_next_extent(fieinfo, logical, phys,
+ size, flags);
+ if (ret)
+ break;
+ }
+ cond_resched();
+ } while (1);
+
+ mutex_unlock(&inode->i_mutex);
+
+ /* if ret is 1 then we just hit the end of the extent array */
+ if (ret == 1)
+ ret = 0;
+
+ return ret;
+}
+EXPORT_SYMBOL(generic_block_fiemap);
+
static int file_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
{
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 80171ee..8120fa1 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -837,6 +837,8 @@ extern void ext3_truncate (struct inode *);
extern void ext3_set_inode_flags(struct inode *);
extern void ext3_get_inode_flags(struct ext3_inode_info *);
extern void ext3_set_aops(struct inode *inode);
+extern int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len);
/* ioctl.c */
extern int ext3_ioctl (struct inode *, struct file *, unsigned int,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 194fb23..385c9a1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1998,6 +1998,9 @@ extern int vfs_fstat(unsigned int, struct kstat *);
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
unsigned long arg);
+extern int generic_block_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo, u64 start,
+ u64 len, get_block_t *get_block);
extern void get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
--
1.5.6.1.205.ge2c7.dirty
^ permalink raw reply related [flat|nested] 13+ messages in thread
* [PATCH 3/4] generic block based fiemap implementation
2008-10-03 21:59 ` [PATCH 2/4] ocfs2: fiemap support Theodore Ts'o
@ 2008-10-03 21:59 ` Theodore Ts'o
2008-10-06 11:35 ` steve
0 siblings, 1 reply; 13+ messages in thread
From: Theodore Ts'o @ 2008-10-03 21:59 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Josef Bacik, Mark Fasheh, Theodore Ts'o
From: Josef Bacik <jbacik@redhat.com>
Any block based fs (this patch includes ext3) just has to declare its own
fiemap() function and then call this generic function with its own
get_block_t. This works well for block based filesystems that will map
multiple contiguous blocks at one time, but will work for filesystems that
only map one block at a time, you will just end up with an "extent" for each
block. One gotcha is this will not play nicely where there is hole+data
after the EOF. This function will assume its hit the end of the data as soon
as it hits a hole after the EOF, so if there is any data past that it will
not pick that up. AFAIK no block based fs does this anyway, but its in the
comments of the function anyway just in case.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: linux-fsdevel@vger.kernel.org
---
fs/ext2/ext2.h | 2 +
fs/ext2/file.c | 1 +
fs/ext2/inode.c | 8 +++
fs/ext3/file.c | 1 +
fs/ext3/inode.c | 8 +++
fs/ioctl.c | 118 +++++++++++++++++++++++++++++++++++++++++++++++
include/linux/ext3_fs.h | 2 +
include/linux/fs.h | 3 +
8 files changed, 143 insertions(+), 0 deletions(-)
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 47d88da..bae998c 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -133,6 +133,8 @@ extern void ext2_truncate (struct inode *);
extern int ext2_setattr (struct dentry *, struct iattr *);
extern void ext2_set_inode_flags(struct inode *inode);
extern void ext2_get_inode_flags(struct ext2_inode_info *);
+extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len);
int __ext2_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata);
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 5f2fa9c..45ed071 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -86,4 +86,5 @@ const struct inode_operations ext2_file_inode_operations = {
#endif
.setattr = ext2_setattr,
.permission = ext2_permission,
+ .fiemap = ext2_fiemap,
};
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 991d6df..7658b33 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -31,6 +31,7 @@
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
+#include <linux/fiemap.h>
#include "ext2.h"
#include "acl.h"
#include "xip.h"
@@ -704,6 +705,13 @@ int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_
}
+int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ return generic_block_fiemap(inode, fieinfo, start, len,
+ ext2_get_block);
+}
+
static int ext2_writepage(struct page *page, struct writeback_control *wbc)
{
return block_write_full_page(page, ext2_get_block, wbc);
diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index acc4913..3be1e06 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -134,5 +134,6 @@ const struct inode_operations ext3_file_inode_operations = {
.removexattr = generic_removexattr,
#endif
.permission = ext3_permission,
+ .fiemap = ext3_fiemap,
};
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 507d868..ebfec4d 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -36,6 +36,7 @@
#include <linux/mpage.h>
#include <linux/uio.h>
#include <linux/bio.h>
+#include <linux/fiemap.h>
#include "xattr.h"
#include "acl.h"
@@ -981,6 +982,13 @@ out:
return ret;
}
+int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ return generic_block_fiemap(inode, fieinfo, start, len,
+ ext3_get_block);
+}
+
/*
* `handle' can be NULL if create is zero
*/
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 837444a..9019510 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -13,6 +13,8 @@
#include <linux/security.h>
#include <linux/module.h>
#include <linux/uaccess.h>
+#include <linux/writeback.h>
+#include <linux/buffer_head.h>
#include <asm/ioctls.h>
@@ -224,6 +226,122 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg)
return error;
}
+#define blk_to_logical(inode, blk) (blk << (inode)->i_blkbits)
+#define logical_to_blk(inode, offset) (offset >> (inode)->i_blkbits);
+
+/*
+ * @inode - the inode to map
+ * @arg - the pointer to userspace where we copy everything to
+ * @get_block - the fs's get_block function
+ *
+ * This does FIEMAP for block based inodes. Basically it will just loop
+ * through get_block until we hit the number of extents we want to map, or we
+ * go past the end of the file and hit a hole.
+ *
+ * If it is possible to have data blocks beyond a hole past @inode->i_size, then
+ * please do not use this function, it will stop at the first unmapped block
+ * beyond i_size
+ */
+int generic_block_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo, u64 start,
+ u64 len, get_block_t *get_block)
+{
+ struct buffer_head tmp;
+ unsigned int start_blk;
+ long long length = 0, map_len = 0;
+ u64 logical = 0, phys = 0, size = 0;
+ u32 flags = FIEMAP_EXTENT_MERGED;
+ int ret = 0;
+
+ if ((ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC)))
+ return ret;
+
+ start_blk = logical_to_blk(inode, start);
+
+ /* guard against change */
+ mutex_lock(&inode->i_mutex);
+
+ length = (long long)min_t(u64, len, i_size_read(inode));
+ map_len = length;
+
+ do {
+ /*
+ * we set b_size to the total size we want so it will map as
+ * many contiguous blocks as possible at once
+ */
+ memset(&tmp, 0, sizeof(struct buffer_head));
+ tmp.b_size = map_len;
+
+ ret = get_block(inode, start_blk, &tmp, 0);
+ if (ret)
+ break;
+
+ /* HOLE */
+ if (!buffer_mapped(&tmp)) {
+ /*
+ * first hole after going past the EOF, this is our
+ * last extent
+ */
+ if (length <= 0) {
+ flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size,
+ flags);
+ break;
+ }
+
+ length -= blk_to_logical(inode, 1);
+
+ /* if we have holes up to/past EOF then we're done */
+ if (length <= 0)
+ break;
+
+ start_blk++;
+ } else {
+ if (length <= 0 && size) {
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size,
+ flags);
+ if (ret)
+ break;
+ }
+
+ logical = blk_to_logical(inode, start_blk);
+ phys = blk_to_logical(inode, tmp.b_blocknr);
+ size = tmp.b_size;
+ flags = FIEMAP_EXTENT_MERGED;
+
+ length -= tmp.b_size;
+ start_blk += logical_to_blk(inode, size);
+
+ /*
+ * if we are past the EOF we need to loop again to see
+ * if there is a hole so we can mark this extent as the
+ * last one, and if not keep mapping things until we
+ * find a hole, or we run out of slots in the extent
+ * array
+ */
+ if (length <= 0)
+ continue;
+
+ ret = fiemap_fill_next_extent(fieinfo, logical, phys,
+ size, flags);
+ if (ret)
+ break;
+ }
+ cond_resched();
+ } while (1);
+
+ mutex_unlock(&inode->i_mutex);
+
+ /* if ret is 1 then we just hit the end of the extent array */
+ if (ret == 1)
+ ret = 0;
+
+ return ret;
+}
+EXPORT_SYMBOL(generic_block_fiemap);
+
static int file_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
{
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 80171ee..8120fa1 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -837,6 +837,8 @@ extern void ext3_truncate (struct inode *);
extern void ext3_set_inode_flags(struct inode *);
extern void ext3_get_inode_flags(struct ext3_inode_info *);
extern void ext3_set_aops(struct inode *inode);
+extern int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len);
/* ioctl.c */
extern int ext3_ioctl (struct inode *, struct file *, unsigned int,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0724abf..6242491 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1999,6 +1999,9 @@ extern int vfs_fstat(unsigned int, struct kstat *);
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
unsigned long arg);
+extern int generic_block_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo, u64 start,
+ u64 len, get_block_t *get_block);
extern void get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
--
1.5.6.1.205.ge2c7.dirty
^ permalink raw reply related [flat|nested] 13+ messages in thread
* Re: [PATCH 3/4] generic block based fiemap implementation
2008-10-03 21:59 ` [PATCH 3/4] generic block based fiemap implementation Theodore Ts'o
@ 2008-10-06 11:35 ` steve
2008-10-06 21:14 ` Theodore Tso
0 siblings, 1 reply; 13+ messages in thread
From: steve @ 2008-10-06 11:35 UTC (permalink / raw)
To: Theodore Ts'o; +Cc: linux-fsdevel, Josef Bacik, Mark Fasheh
Hi,
On Fri, Oct 03, 2008 at 05:59:06PM -0400, Theodore Ts'o wrote:
> From: Josef Bacik <jbacik@redhat.com>
>
> Any block based fs (this patch includes ext3) just has to declare its own
> fiemap() function and then call this generic function with its own
> get_block_t. This works well for block based filesystems that will map
> multiple contiguous blocks at one time, but will work for filesystems that
> only map one block at a time, you will just end up with an "extent" for each
> block. One gotcha is this will not play nicely where there is hole+data
> after the EOF. This function will assume its hit the end of the data as soon
> as it hits a hole after the EOF, so if there is any data past that it will
> not pick that up. AFAIK no block based fs does this anyway, but its in the
> comments of the function anyway just in case.
>
> Signed-off-by: Josef Bacik <jbacik@redhat.com>
> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
> Cc: linux-fsdevel@vger.kernel.org
Would it be possible to move the inode mutex out of generic_block_fiemap()
and into the callers? The defined lock ordering in GFS2 is inode mutex ->
inode glock, and thus we want to be able to lock in that order. We should
be able to use generic_block_fiemap() for GFS2 in that case. Thanks,
Steve.
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH 3/4] generic block based fiemap implementation
2008-10-06 11:35 ` steve
@ 2008-10-06 21:14 ` Theodore Tso
2008-10-07 8:14 ` steve
0 siblings, 1 reply; 13+ messages in thread
From: Theodore Tso @ 2008-10-06 21:14 UTC (permalink / raw)
To: steve; +Cc: linux-fsdevel, Josef Bacik, Mark Fasheh
On Mon, Oct 06, 2008 at 12:35:06PM +0100, steve@chygwyn.com wrote:
>
> Would it be possible to move the inode mutex out of generic_block_fiemap()
> and into the callers? The defined lock ordering in GFS2 is inode mutex ->
> inode glock, and thus we want to be able to lock in that order. We should
> be able to use generic_block_fiemap() for GFS2 in that case.
Given that nearly all other block-based filesystems that don't use
extents would need to take the mutex lock, this would be error-prone.
What about introducing an _generic_block_fiemap() for use by GFS2 that
doesn't the inode mutex, and changing generic_block_fiemap() to be a
wrapper that calls _generic_block_fiemap() and takes the inode mutex
for the convenience of most other filesystems?
This would be a very simple change to make once a patch to enable GFS2
use of the FIEMAP interface. (If we introduce
_generic_block_fiemap(), it's likely to get removed by some random
roving Kernel Janitor, as an exported but unused interface. :-)
It occurs to me though that this is likely not all that is needed for
GFS2, though, since like Lustre, BTRFS, and ZFS, there can be multiple
disks or storage devices associated with a single filesystem, correct?
So we would need to add some way of identifying the disk, not just the
block number; how does GFS2 identify/enumerate storage devices which
are part of a particular filesystem?
- Ted
^ permalink raw reply [flat|nested] 13+ messages in thread
* PATCH [0/4] Updated**2 fiemap patches
@ 2008-10-07 1:06 Theodore Ts'o
2008-10-07 1:06 ` [PATCH 1/4] vfs: vfs-level fiemap interface Theodore Ts'o
0 siblings, 1 reply; 13+ messages in thread
From: Theodore Ts'o @ 2008-10-07 1:06 UTC (permalink / raw)
To: linux-fsdevel
This the second update of the fiemap patches, which integrates the
changes and typographical fixups as suggested by Jim Owens. In
particular, FIEMAP_EXTENT_NO_MOUNTED_IO was renamed to what I had
intended, but mistyped, FIEMAP_EXTENT_NO_UNMOUNTED_IO, and the
explanation of that flag has been clarified.
Hopefully folks are happy with this. I plan to push this to Linus
when the next merge window opens up.
- Ted
^ permalink raw reply [flat|nested] 13+ messages in thread
* [PATCH 1/4] vfs: vfs-level fiemap interface
2008-10-07 1:06 PATCH [0/4] Updated**2 fiemap patches Theodore Ts'o
@ 2008-10-07 1:06 ` Theodore Ts'o
2008-10-07 1:06 ` [PATCH 2/4] ocfs2: fiemap support Theodore Ts'o
[not found] ` <1223341581-13802-2-git-send-email-tytso-3s7WtUTddSA@public.gmane.org>
0 siblings, 2 replies; 13+ messages in thread
From: Theodore Ts'o @ 2008-10-07 1:06 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Mark Fasheh, Theodore Ts'o, Michael Kerrisk, linux-abi
From: Mark Fasheh <mfasheh@suse.com>
Basic vfs-level fiemap infrastructure, which sets up a new ->fiemap
inode operation.
Userspace can get extent information on a file via fiemap ioctl. As input,
the fiemap ioctl takes a struct fiemap which includes an array of struct
fiemap_extent (fm_extents). Size of the extent array is passed as
fm_extent_count and number of extents returned will be written into
fm_mapped_extents. Offset and length fields on the fiemap structure
(fm_start, fm_length) describe a logical range which will be searched for
extents. All extents returned will at least partially contain this range.
The actual extent offsets and ranges returned will be unmodified from their
offset and range on-disk.
The fiemap ioctl returns '0' on success. On error, -1 is returned and errno
is set. If errno is equal to EBADR, then fm_flags will contain those flags
which were passed in which the kernel did not understand. On all other
errors, the contents of fm_extents is undefined.
As fiemap evolved, there have been many authors of the vfs patch. As far as
I can tell, the list includes:
Kalpak Shah <kalpak.shah@sun.com>
Andreas Dilger <adilger@sun.com>
Eric Sandeen <sandeen@redhat.com>
Mark Fasheh <mfasheh@suse.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: linux-abi@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org
---
Documentation/filesystems/fiemap.txt | 221 ++++++++++++++++++++++++++++++++++
fs/ioctl.c | 155 ++++++++++++++++++++++++
include/linux/fiemap.h | 64 ++++++++++
include/linux/fs.h | 18 +++
4 files changed, 458 insertions(+), 0 deletions(-)
create mode 100644 Documentation/filesystems/fiemap.txt
create mode 100644 include/linux/fiemap.h
diff --git a/Documentation/filesystems/fiemap.txt b/Documentation/filesystems/fiemap.txt
new file mode 100644
index 0000000..d56b30e
--- /dev/null
+++ b/Documentation/filesystems/fiemap.txt
@@ -0,0 +1,221 @@
+============
+Fiemap Ioctl
+============
+
+The fiemap ioctl is an efficient method for userspace to get file
+extent mappings. Instead of block-by-block mapping (such as bmap), fiemap
+returns a list of extents.
+
+
+Request Basics
+--------------
+
+A fiemap request is encoded within struct fiemap:
+
+struct fiemap {
+ __u64 fm_start; /* logical offset (inclusive) at
+ * which to start mapping (in) */
+ __u64 fm_length; /* logical length of mapping which
+ * userspace cares about (in) */
+ __u32 fm_flags; /* FIEMAP_FLAG_* flags for request (in/out) */
+ __u32 fm_mapped_extents; /* number of extents that were
+ * mapped (out) */
+ __u32 fm_extent_count; /* size of fm_extents array (in) */
+ __u32 fm_reserved;
+ struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */
+};
+
+
+fm_start, and fm_length specify the logical range within the file
+which the process would like mappings for. Extents returned mirror
+those on disk - that is, the logical offset of the 1st returned extent
+may start before fm_start, and the range covered by the last returned
+extent may end after fm_length. All offsets and lengths are in bytes.
+
+Certain flags to modify the way in which mappings are looked up can be
+set in fm_flags. If the kernel doesn't understand some particular
+flags, it will return EBADR and the contents of fm_flags will contain
+the set of flags which caused the error. If the kernel is compatible
+with all flags passed, the contents of fm_flags will be unmodified.
+It is up to userspace to determine whether rejection of a particular
+flag is fatal to it's operation. This scheme is intended to allow the
+fiemap interface to grow in the future but without losing
+compatibility with old software.
+
+fm_extent_count specifies the number of elements in the fm_extents[] array
+that can be used to return extents. If fm_extent_count is zero, then the
+fm_extents[] array is ignored (no extents will be returned), and the
+fm_mapped_extents count will hold the number of extents needed in
+fm_extents[] to hold the file's current mapping. Note that there is
+nothing to prevent the file from changing between calls to FIEMAP.
+
+The following flags can be set in fm_flags:
+
+* FIEMAP_FLAG_SYNC
+If this flag is set, the kernel will sync the file before mapping extents.
+
+* FIEMAP_FLAG_XATTR
+If this flag is set, the extents returned will describe the inodes
+extended attribute lookup tree, instead of it's data tree.
+
+
+Extent Mapping
+--------------
+
+Extent information is returned within the embedded fm_extents array
+which userspace must allocate along with the fiemap structure. The
+number of elements in the fiemap_extents[] array should be passed via
+fm_extent_count. The number of extents mapped by kernel will be
+returned via fm_mapped_extents. If the number of fiemap_extents
+allocated is less than would be required to map the requested range,
+the maximum number of extents that can be mapped in the fm_extent[]
+array will be returned and fm_mapped_extents will be equal to
+fm_extent_count. In that case, the last extent in the array will not
+complete the requested range and will not have the FIEMAP_EXTENT_LAST
+flag set (see the next section on extent flags).
+
+Each extent is described by a single fiemap_extent structure as
+returned in fm_extents.
+
+struct fiemap_extent {
+ __u64 fe_logical; /* logical offset in bytes for the start of
+ * the extent */
+ __u64 fe_physical; /* physical offset in bytes for the start
+ * of the extent */
+ __u64 fe_length; /* length in bytes for the extent */
+ __u64 fe_reserved64[2];
+ __u32 fe_flags; /* FIEMAP_EXTENT_* flags for this extent */
+ __u32 fe_reserved[3];
+};
+
+All offsets and lengths are in bytes and mirror those on disk. It is valid
+for an extents logical offset to start before the request or it's logical
+length to extend past the request. Unless FIEMAP_EXTENT_NOT_ALIGNED is
+returned, fe_logical, fe_physical, and fe_length will be aligned to the
+block size of the file system. With the exception of extents flagged as
+FIEMAP_EXTENT_MERGED, adjacent extents will not be merged.
+
+The fe_flags field contains flags which describe the extent returned.
+A special flag, FIEMAP_EXTENT_LAST is always set on the last extent in
+the file so that the process making fiemap calls can determine when no
+more extents are available, without having to call the ioctl again.
+
+Some flags are intentionally vague and will always be set in the
+presence of other more specific flags. This way a program looking for
+a general property does not have to know all existing and future flags
+which imply that property.
+
+For example, if FIEMAP_EXTENT_DATA_INLINE or FIEMAP_EXTENT_DATA_TAIL
+are set, FIEMAP_EXTENT_NOT_ALIGNED will also be set. A program looking
+for inline or tail-packed data can key on the specific flag. Software
+which simply cares not to try operating on non-aligned extents
+however, can just key on FIEMAP_EXTENT_NOT_ALIGNED, and not have to
+worry about all present and future flags which might imply unaligned
+data. Note that the opposite is not true - it would be valid for
+FIEMAP_EXTENT_NOT_ALIGNED to appear alone.
+
+* FIEMAP_EXTENT_LAST
+This is the last extent in the file. A mapping attempt past this
+extent will return nothing.
+
+* FIEMAP_EXTENT_UNKNOWN
+The location of this extent is currently unknown. This may indicate
+the data is stored on an inaccessible volume or that no storage has
+been allocated for the file yet.
+
+* FIEMAP_EXTENT_DELALLOC
+ - This will also set FIEMAP_EXTENT_UNKNOWN.
+Delayed allocation - while there is data for this extent, it's
+physical location has not been allocated yet.
+
+* FIEMAP_EXTENT_NO_UNMOUNTED_IO
+Accessing the data in this extent via I/O to the block device while the
+filesystem is unmounted is illegal or will have undefined results. This
+may because the data is somehow encrypted or compressed by the filesystem.
+Note that accessing the data using the information returned by the
+FIEMAP interface while the filesystem is mounted is *always* undefined
+should not be attempted by user applications.
+
+* FIEMAP_EXTENT_DATA_ENCRYPTED
+ - This will also set FIEMAP_EXTENT_NO_UNMOUNTED_IO
+The data in this extent has been encrypted by the file system.
+
+* FIEMAP_EXTENT_NOT_ALIGNED
+Extent offsets and length are not guaranteed to be block aligned.
+
+* FIEMAP_EXTENT_DATA_INLINE
+ This will also set FIEMAP_EXTENT_NOT_ALIGNED
+Data is located within a meta data block.
+
+* FIEMAP_EXTENT_DATA_TAIL
+ This will also set FIEMAP_EXTENT_NOT_ALIGNED
+Data is packed into a block with data from other files.
+
+* FIEMAP_EXTENT_UNWRITTEN
+Unwritten extent - the extent is allocated but it's data has not been
+initialized. This indicates the extent's data will be all zero if read
+through the filesystem but the contents are undefined if read directly from
+the device.
+
+* FIEMAP_EXTENT_MERGED
+This will be set when a file does not support extents, i.e., it uses a block
+based addressing scheme. Since returning an extent for each block back to
+userspace would be highly inefficient, the kernel will try to merge most
+adjacent blocks into 'extents'.
+
+
+VFS -> File System Implementation
+---------------------------------
+
+File systems wishing to support fiemap must implement a ->fiemap callback on
+their inode_operations structure. The fs ->fiemap call is responsible for
+defining it's set of supported fiemap flags, and calling a helper function on
+each discovered extent:
+
+struct inode_operations {
+ ...
+
+ int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
+ u64 len);
+
+->fiemap is passed struct fiemap_extent_info which describes the
+fiemap request:
+
+struct fiemap_extent_info {
+ unsigned int fi_flags; /* Flags as passed from user */
+ unsigned int fi_extents_mapped; /* Number of mapped extents */
+ unsigned int fi_extents_max; /* Size of fiemap_extent array */
+ struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent array */
+};
+
+It is intended that the file system should not need to access any of this
+structure directly.
+
+
+Flag checking should be done at the beginning of the ->fiemap callback via the
+fiemap_check_flags() helper:
+
+int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
+
+The struct fieinfo should be passed in as recieved from ioctl_fiemap(). The
+set of fiemap flags which the fs understands should be passed via fs_flags. If
+fiemap_check_flags finds invalid user flags, it will place the bad values in
+fieinfo->fi_flags and return -EBADR. If the file system gets -EBADR, from
+fiemap_check_flags(), it should immediately exit, returning that error back to
+ioctl_fiemap().
+
+
+For each extent in the request range, the file system should call
+the helper function, fiemap_fill_next_extent():
+
+int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
+ u64 phys, u64 len, u32 flags, u32 dev);
+
+fiemap_fill_next_extent() will use the passed values to populate the
+next free extent in the fm_extents array. 'General' extent flags will
+automatically be set from specific flags on behalf of the calling file
+system so that the userspace API is not broken.
+
+fiemap_fill_next_extent() returns 0 on success, and 1 when the
+user-supplied fm_extents array is full. If an error is encountered
+while copying the extent to user memory, -EFAULT will be returned.
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 7db32b3..b759cc2 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -16,6 +16,9 @@
#include <asm/ioctls.h>
+/* So that the fiemap access checks can't overflow on 32 bit machines. */
+#define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent))
+
/**
* vfs_ioctl - call filesystem specific ioctl methods
* @filp: open file to invoke ioctl method on
@@ -71,6 +74,156 @@ static int ioctl_fibmap(struct file *filp, int __user *p)
return put_user(res, p);
}
+/**
+ * fiemap_fill_next_extent - Fiemap helper function
+ * @fieinfo: Fiemap context passed into ->fiemap
+ * @logical: Extent logical start offset, in bytes
+ * @phys: Extent physical start offset, in bytes
+ * @len: Extent length, in bytes
+ * @flags: FIEMAP_EXTENT flags that describe this extent
+ *
+ * Called from file system ->fiemap callback. Will populate extent
+ * info as passed in via arguments and copy to user memory. On
+ * success, extent count on fieinfo is incremented.
+ *
+ * Returns 0 on success, -errno on error, 1 if this was the last
+ * extent that will fit in user array.
+ */
+#define SET_UNKNOWN_FLAGS (FIEMAP_EXTENT_DELALLOC)
+#define SET_NO_UNMOUNTED_IO_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED)
+#define SET_NOT_ALIGNED_FLAGS (FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE)
+int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical,
+ u64 phys, u64 len, u32 flags)
+{
+ struct fiemap_extent extent;
+ struct fiemap_extent *dest = fieinfo->fi_extents_start;
+
+ /* only count the extents */
+ if (fieinfo->fi_extents_max == 0) {
+ fieinfo->fi_extents_mapped++;
+ return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
+ }
+
+ if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max)
+ return 1;
+
+ if (flags & SET_UNKNOWN_FLAGS)
+ flags |= FIEMAP_EXTENT_UNKNOWN;
+ if (flags & SET_NO_UNMOUNTED_IO_FLAGS)
+ flags |= FIEMAP_EXTENT_NO_UNMOUNTED_IO;
+ if (flags & SET_NOT_ALIGNED_FLAGS)
+ flags |= FIEMAP_EXTENT_NOT_ALIGNED;
+
+ memset(&extent, 0, sizeof(extent));
+ extent.fe_logical = logical;
+ extent.fe_physical = phys;
+ extent.fe_length = len;
+ extent.fe_flags = flags;
+
+ dest += fieinfo->fi_extents_mapped;
+ if (copy_to_user(dest, &extent, sizeof(extent)))
+ return -EFAULT;
+
+ fieinfo->fi_extents_mapped++;
+ if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max)
+ return 1;
+ return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
+}
+EXPORT_SYMBOL(fiemap_fill_next_extent);
+
+/**
+ * fiemap_check_flags - check validity of requested flags for fiemap
+ * @fieinfo: Fiemap context passed into ->fiemap
+ * @fs_flags: Set of fiemap flags that the file system understands
+ *
+ * Called from file system ->fiemap callback. This will compute the
+ * intersection of valid fiemap flags and those that the fs supports. That
+ * value is then compared against the user supplied flags. In case of bad user
+ * flags, the invalid values will be written into the fieinfo structure, and
+ * -EBADR is returned, which tells ioctl_fiemap() to return those values to
+ * userspace. For this reason, a return code of -EBADR should be preserved.
+ *
+ * Returns 0 on success, -EBADR on bad flags.
+ */
+int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags)
+{
+ u32 incompat_flags;
+
+ incompat_flags = fieinfo->fi_flags & ~(FIEMAP_FLAGS_COMPAT & fs_flags);
+ if (incompat_flags) {
+ fieinfo->fi_flags = incompat_flags;
+ return -EBADR;
+ }
+ return 0;
+}
+EXPORT_SYMBOL(fiemap_check_flags);
+
+static int fiemap_check_ranges(struct super_block *sb,
+ u64 start, u64 len, u64 *new_len)
+{
+ *new_len = len;
+
+ if (len == 0)
+ return -EINVAL;
+
+ if (start > sb->s_maxbytes)
+ return -EFBIG;
+
+ /*
+ * Shrink request scope to what the fs can actually handle.
+ */
+ if ((len > sb->s_maxbytes) ||
+ (sb->s_maxbytes - len) < start)
+ *new_len = sb->s_maxbytes - start;
+
+ return 0;
+}
+
+static int ioctl_fiemap(struct file *filp, unsigned long arg)
+{
+ struct fiemap fiemap;
+ struct fiemap_extent_info fieinfo = { 0, };
+ struct inode *inode = filp->f_path.dentry->d_inode;
+ struct super_block *sb = inode->i_sb;
+ u64 len;
+ int error;
+
+ if (!inode->i_op->fiemap)
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&fiemap, (struct fiemap __user *)arg,
+ sizeof(struct fiemap)))
+ return -EFAULT;
+
+ if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS)
+ return -EINVAL;
+
+ error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length,
+ &len);
+ if (error)
+ return error;
+
+ fieinfo.fi_flags = fiemap.fm_flags;
+ fieinfo.fi_extents_max = fiemap.fm_extent_count;
+ fieinfo.fi_extents_start = (struct fiemap_extent *)(arg + sizeof(fiemap));
+
+ if (fiemap.fm_extent_count != 0 &&
+ !access_ok(VERIFY_WRITE, fieinfo.fi_extents_start,
+ fieinfo.fi_extents_max * sizeof(struct fiemap_extent)))
+ return -EFAULT;
+
+ if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC)
+ filemap_write_and_wait(inode->i_mapping);
+
+ error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, len);
+ fiemap.fm_flags = fieinfo.fi_flags;
+ fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped;
+ if (copy_to_user((char *)arg, &fiemap, sizeof(fiemap)))
+ error = -EFAULT;
+
+ return error;
+}
+
static int file_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
{
@@ -80,6 +233,8 @@ static int file_ioctl(struct file *filp, unsigned int cmd,
switch (cmd) {
case FIBMAP:
return ioctl_fibmap(filp, p);
+ case FS_IOC_FIEMAP:
+ return ioctl_fiemap(filp, arg);
case FIGETBSZ:
return put_user(inode->i_sb->s_blocksize, p);
case FIONREAD:
diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h
new file mode 100644
index 0000000..cbc51e6
--- /dev/null
+++ b/include/linux/fiemap.h
@@ -0,0 +1,64 @@
+/*
+ * FS_IOC_FIEMAP ioctl infrastructure.
+ *
+ * Some portions copyright (C) 2007 Cluster File Systems, Inc
+ *
+ * Authors: Mark Fasheh <mfasheh@suse.com>
+ * Kalpak Shah <kalpak.shah@sun.com>
+ * Andreas Dilger <adilger@sun.com>
+ */
+
+#ifndef _LINUX_FIEMAP_H
+#define _LINUX_FIEMAP_H
+
+struct fiemap_extent {
+ __u64 fe_logical; /* logical offset in bytes for the start of
+ * the extent from the beginning of the file */
+ __u64 fe_physical; /* physical offset in bytes for the start
+ * of the extent from the beginning of the disk */
+ __u64 fe_length; /* length in bytes for this extent */
+ __u64 fe_reserved64[2];
+ __u32 fe_flags; /* FIEMAP_EXTENT_* flags for this extent */
+ __u32 fe_reserved[3];
+};
+
+struct fiemap {
+ __u64 fm_start; /* logical offset (inclusive) at
+ * which to start mapping (in) */
+ __u64 fm_length; /* logical length of mapping which
+ * userspace wants (in) */
+ __u32 fm_flags; /* FIEMAP_FLAG_* flags for request (in/out) */
+ __u32 fm_mapped_extents;/* number of extents that were mapped (out) */
+ __u32 fm_extent_count; /* size of fm_extents array (in) */
+ __u32 fm_reserved;
+ struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */
+};
+
+#define FIEMAP_MAX_OFFSET (~0ULL)
+
+#define FIEMAP_FLAG_SYNC 0x00000001 /* sync file data before map */
+#define FIEMAP_FLAG_XATTR 0x00000002 /* map extended attribute tree */
+
+#define FIEMAP_FLAGS_COMPAT (FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR)
+
+#define FIEMAP_EXTENT_LAST 0x00000001 /* Last extent in file. */
+#define FIEMAP_EXTENT_UNKNOWN 0x00000002 /* Data location unknown. */
+#define FIEMAP_EXTENT_DELALLOC 0x00000004 /* Location still pending.
+ * Sets EXTENT_UNKNOWN. */
+#define FIEMAP_EXTENT_NO_UNMOUNTED_IO 0x00000008 /* Data can not be read
+ * while fs is unmounted */
+#define FIEMAP_EXTENT_DATA_ENCRYPTED 0x00000080 /* Data is encrypted by fs.
+ * Sets EXTENT_NO_BYPASS. */
+#define FIEMAP_EXTENT_NOT_ALIGNED 0x00000100 /* Extent offsets may not be
+ * block aligned. */
+#define FIEMAP_EXTENT_DATA_INLINE 0x00000200 /* Data mixed with metadata.
+ * Sets EXTENT_NOT_ALIGNED.*/
+#define FIEMAP_EXTENT_DATA_TAIL 0x00000400 /* Multiple files in block.
+ * Sets EXTENT_NOT_ALIGNED.*/
+#define FIEMAP_EXTENT_UNWRITTEN 0x00000800 /* Space allocated, but
+ * no data (i.e. zero). */
+#define FIEMAP_EXTENT_MERGED 0x00001000 /* File does not natively
+ * support extents. Result
+ * merged for efficiency. */
+
+#endif /* _LINUX_FIEMAP_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 580b513..194fb23 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -231,6 +231,7 @@ extern int dir_notify_enable;
#define FS_IOC_SETFLAGS _IOW('f', 2, long)
#define FS_IOC_GETVERSION _IOR('v', 1, long)
#define FS_IOC_SETVERSION _IOW('v', 2, long)
+#define FS_IOC_FIEMAP _IOWR('f', 11, struct fiemap)
#define FS_IOC32_GETFLAGS _IOR('f', 1, int)
#define FS_IOC32_SETFLAGS _IOW('f', 2, int)
#define FS_IOC32_GETVERSION _IOR('v', 1, int)
@@ -291,6 +292,7 @@ extern int dir_notify_enable;
#include <linux/mutex.h>
#include <linux/capability.h>
#include <linux/semaphore.h>
+#include <linux/fiemap.h>
#include <asm/atomic.h>
#include <asm/byteorder.h>
@@ -1179,6 +1181,20 @@ extern void dentry_unhash(struct dentry *dentry);
extern int file_permission(struct file *, int);
/*
+ * VFS FS_IOC_FIEMAP helper definitions.
+ */
+struct fiemap_extent_info {
+ unsigned int fi_flags; /* Flags as passed from user */
+ unsigned int fi_extents_mapped; /* Number of mapped extents */
+ unsigned int fi_extents_max; /* Size of fiemap_extent array */
+ struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent
+ * array */
+};
+int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
+ u64 phys, u64 len, u32 flags);
+int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
+
+/*
* File types
*
* NOTE! These match bits 12..15 of stat.st_mode
@@ -1287,6 +1303,8 @@ struct inode_operations {
void (*truncate_range)(struct inode *, loff_t, loff_t);
long (*fallocate)(struct inode *inode, int mode, loff_t offset,
loff_t len);
+ int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
+ u64 len);
};
struct seq_file;
--
1.5.6.1.205.ge2c7.dirty
^ permalink raw reply related [flat|nested] 13+ messages in thread
* [PATCH 2/4] ocfs2: fiemap support
2008-10-07 1:06 ` [PATCH 1/4] vfs: vfs-level fiemap interface Theodore Ts'o
@ 2008-10-07 1:06 ` Theodore Ts'o
2008-10-07 1:06 ` [PATCH 3/4] generic block based fiemap implementation Theodore Ts'o
[not found] ` <1223341581-13802-2-git-send-email-tytso-3s7WtUTddSA@public.gmane.org>
1 sibling, 1 reply; 13+ messages in thread
From: Theodore Ts'o @ 2008-10-07 1:06 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Mark Fasheh, Theodore Ts'o, ocfs2-devel
From: Mark Fasheh <mfasheh@suse.com>
Plug ocfs2 into ->fiemap. Some portions of ocfs2_get_clusters() had to be
refactored so that the extent cache can be skipped in favor of going
directly to the on-disk records. This makes it easier for us to determine
which extent is the last one in the btree. Also, I'm not sure we want to be
caching fiemap lookups anyway as they're not directly related to data
read/write.
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: ocfs2-devel@oss.oracle.com
Cc: linux-fsdevel@vger.kernel.org
---
fs/ocfs2/alloc.c | 9 --
fs/ocfs2/alloc.h | 9 ++
fs/ocfs2/extent_map.c | 346 +++++++++++++++++++++++++++++++++++++++++--------
fs/ocfs2/extent_map.h | 3 +
fs/ocfs2/file.c | 1 +
5 files changed, 306 insertions(+), 62 deletions(-)
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 10bfb46..29ff57e 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -990,15 +990,6 @@ out:
}
/*
- * This is only valid for leaf nodes, which are the only ones that can
- * have empty extents anyway.
- */
-static inline int ocfs2_is_empty_extent(struct ocfs2_extent_rec *rec)
-{
- return !rec->e_leaf_clusters;
-}
-
-/*
* This function will discard the rightmost extent record.
*/
static void ocfs2_shift_records_right(struct ocfs2_extent_list *el)
diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
index 42ff94b..60cd3d5 100644
--- a/fs/ocfs2/alloc.h
+++ b/fs/ocfs2/alloc.h
@@ -146,4 +146,13 @@ static inline unsigned int ocfs2_rec_clusters(struct ocfs2_extent_list *el,
return le16_to_cpu(rec->e_leaf_clusters);
}
+/*
+ * This is only valid for leaf nodes, which are the only ones that can
+ * have empty extents anyway.
+ */
+static inline int ocfs2_is_empty_extent(struct ocfs2_extent_rec *rec)
+{
+ return !rec->e_leaf_clusters;
+}
+
#endif /* OCFS2_ALLOC_H */
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index c58668a..aed268e 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -25,6 +25,7 @@
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/types.h>
+#include <linux/fiemap.h>
#define MLOG_MASK_PREFIX ML_EXTENT_MAP
#include <cluster/masklog.h>
@@ -32,6 +33,7 @@
#include "ocfs2.h"
#include "alloc.h"
+#include "dlmglue.h"
#include "extent_map.h"
#include "inode.h"
#include "super.h"
@@ -282,6 +284,51 @@ out:
kfree(new_emi);
}
+static int ocfs2_last_eb_is_empty(struct inode *inode,
+ struct ocfs2_dinode *di)
+{
+ int ret, next_free;
+ u64 last_eb_blk = le64_to_cpu(di->i_last_eb_blk);
+ struct buffer_head *eb_bh = NULL;
+ struct ocfs2_extent_block *eb;
+ struct ocfs2_extent_list *el;
+
+ ret = ocfs2_read_block(OCFS2_SB(inode->i_sb), last_eb_blk,
+ &eb_bh, OCFS2_BH_CACHED, inode);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ eb = (struct ocfs2_extent_block *) eb_bh->b_data;
+ el = &eb->h_list;
+
+ if (!OCFS2_IS_VALID_EXTENT_BLOCK(eb)) {
+ ret = -EROFS;
+ OCFS2_RO_ON_INVALID_EXTENT_BLOCK(inode->i_sb, eb);
+ goto out;
+ }
+
+ if (el->l_tree_depth) {
+ ocfs2_error(inode->i_sb,
+ "Inode %lu has non zero tree depth in "
+ "leaf block %llu\n", inode->i_ino,
+ (unsigned long long)eb_bh->b_blocknr);
+ ret = -EROFS;
+ goto out;
+ }
+
+ next_free = le16_to_cpu(el->l_next_free_rec);
+
+ if (next_free == 0 ||
+ (next_free == 1 && ocfs2_is_empty_extent(&el->l_recs[0])))
+ ret = 1;
+
+out:
+ brelse(eb_bh);
+ return ret;
+}
+
/*
* Return the 1st index within el which contains an extent start
* larger than v_cluster.
@@ -373,42 +420,28 @@ out:
return ret;
}
-int ocfs2_get_clusters(struct inode *inode, u32 v_cluster,
- u32 *p_cluster, u32 *num_clusters,
- unsigned int *extent_flags)
+static int ocfs2_get_clusters_nocache(struct inode *inode,
+ struct buffer_head *di_bh,
+ u32 v_cluster, unsigned int *hole_len,
+ struct ocfs2_extent_rec *ret_rec,
+ unsigned int *is_last)
{
- int ret, i;
- unsigned int flags = 0;
- struct buffer_head *di_bh = NULL;
- struct buffer_head *eb_bh = NULL;
+ int i, ret, tree_height, len;
struct ocfs2_dinode *di;
- struct ocfs2_extent_block *eb;
+ struct ocfs2_extent_block *uninitialized_var(eb);
struct ocfs2_extent_list *el;
struct ocfs2_extent_rec *rec;
- u32 coff;
-
- if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
- ret = -ERANGE;
- mlog_errno(ret);
- goto out;
- }
-
- ret = ocfs2_extent_map_lookup(inode, v_cluster, p_cluster,
- num_clusters, extent_flags);
- if (ret == 0)
- goto out;
+ struct buffer_head *eb_bh = NULL;
- ret = ocfs2_read_block(OCFS2_SB(inode->i_sb), OCFS2_I(inode)->ip_blkno,
- &di_bh, OCFS2_BH_CACHED, inode);
- if (ret) {
- mlog_errno(ret);
- goto out;
- }
+ memset(ret_rec, 0, sizeof(*ret_rec));
+ if (is_last)
+ *is_last = 0;
di = (struct ocfs2_dinode *) di_bh->b_data;
el = &di->id2.i_list;
+ tree_height = le16_to_cpu(el->l_tree_depth);
- if (el->l_tree_depth) {
+ if (tree_height > 0) {
ret = ocfs2_find_leaf(inode, el, v_cluster, &eb_bh);
if (ret) {
mlog_errno(ret);
@@ -431,46 +464,143 @@ int ocfs2_get_clusters(struct inode *inode, u32 v_cluster,
i = ocfs2_search_extent_list(el, v_cluster);
if (i == -1) {
/*
- * A hole was found. Return some canned values that
- * callers can key on. If asked for, num_clusters will
- * be populated with the size of the hole.
+ * Holes can be larger than the maximum size of an
+ * extent, so we return their lengths in a seperate
+ * field.
*/
- *p_cluster = 0;
- if (num_clusters) {
+ if (hole_len) {
ret = ocfs2_figure_hole_clusters(inode, el, eb_bh,
- v_cluster,
- num_clusters);
+ v_cluster, &len);
if (ret) {
mlog_errno(ret);
goto out;
}
+
+ *hole_len = len;
}
- } else {
- rec = &el->l_recs[i];
+ goto out_hole;
+ }
- BUG_ON(v_cluster < le32_to_cpu(rec->e_cpos));
+ rec = &el->l_recs[i];
- if (!rec->e_blkno) {
- ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
- "record (%u, %u, 0)", inode->i_ino,
- le32_to_cpu(rec->e_cpos),
- ocfs2_rec_clusters(el, rec));
- ret = -EROFS;
- goto out;
+ BUG_ON(v_cluster < le32_to_cpu(rec->e_cpos));
+
+ if (!rec->e_blkno) {
+ ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
+ "record (%u, %u, 0)", inode->i_ino,
+ le32_to_cpu(rec->e_cpos),
+ ocfs2_rec_clusters(el, rec));
+ ret = -EROFS;
+ goto out;
+ }
+
+ *ret_rec = *rec;
+
+ /*
+ * Checking for last extent is potentially expensive - we
+ * might have to look at the next leaf over to see if it's
+ * empty.
+ *
+ * The first two checks are to see whether the caller even
+ * cares for this information, and if the extent is at least
+ * the last in it's list.
+ *
+ * If those hold true, then the extent is last if any of the
+ * additional conditions hold true:
+ * - Extent list is in-inode
+ * - Extent list is right-most
+ * - Extent list is 2nd to rightmost, with empty right-most
+ */
+ if (is_last) {
+ if (i == (le16_to_cpu(el->l_next_free_rec) - 1)) {
+ if (tree_height == 0)
+ *is_last = 1;
+ else if (eb->h_blkno == di->i_last_eb_blk)
+ *is_last = 1;
+ else if (eb->h_next_leaf_blk == di->i_last_eb_blk) {
+ ret = ocfs2_last_eb_is_empty(inode, di);
+ if (ret < 0) {
+ mlog_errno(ret);
+ goto out;
+ }
+ if (ret == 1)
+ *is_last = 1;
+ }
}
+ }
+
+out_hole:
+ ret = 0;
+out:
+ brelse(eb_bh);
+ return ret;
+}
+
+static void ocfs2_relative_extent_offsets(struct super_block *sb,
+ u32 v_cluster,
+ struct ocfs2_extent_rec *rec,
+ u32 *p_cluster, u32 *num_clusters)
+
+{
+ u32 coff = v_cluster - le32_to_cpu(rec->e_cpos);
+
+ *p_cluster = ocfs2_blocks_to_clusters(sb, le64_to_cpu(rec->e_blkno));
+ *p_cluster = *p_cluster + coff;
+
+ if (num_clusters)
+ *num_clusters = le16_to_cpu(rec->e_leaf_clusters) - coff;
+}
+
+int ocfs2_get_clusters(struct inode *inode, u32 v_cluster,
+ u32 *p_cluster, u32 *num_clusters,
+ unsigned int *extent_flags)
+{
+ int ret;
+ unsigned int uninitialized_var(hole_len), flags = 0;
+ struct buffer_head *di_bh = NULL;
+ struct ocfs2_extent_rec rec;
- coff = v_cluster - le32_to_cpu(rec->e_cpos);
+ if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+ ret = -ERANGE;
+ mlog_errno(ret);
+ goto out;
+ }
- *p_cluster = ocfs2_blocks_to_clusters(inode->i_sb,
- le64_to_cpu(rec->e_blkno));
- *p_cluster = *p_cluster + coff;
+ ret = ocfs2_extent_map_lookup(inode, v_cluster, p_cluster,
+ num_clusters, extent_flags);
+ if (ret == 0)
+ goto out;
- if (num_clusters)
- *num_clusters = ocfs2_rec_clusters(el, rec) - coff;
+ ret = ocfs2_read_block(OCFS2_SB(inode->i_sb), OCFS2_I(inode)->ip_blkno,
+ &di_bh, OCFS2_BH_CACHED, inode);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
- flags = rec->e_flags;
+ ret = ocfs2_get_clusters_nocache(inode, di_bh, v_cluster, &hole_len,
+ &rec, NULL);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
- ocfs2_extent_map_insert_rec(inode, rec);
+ if (rec.e_blkno == 0ULL) {
+ /*
+ * A hole was found. Return some canned values that
+ * callers can key on. If asked for, num_clusters will
+ * be populated with the size of the hole.
+ */
+ *p_cluster = 0;
+ if (num_clusters) {
+ *num_clusters = hole_len;
+ }
+ } else {
+ ocfs2_relative_extent_offsets(inode->i_sb, v_cluster, &rec,
+ p_cluster, num_clusters);
+ flags = rec.e_flags;
+
+ ocfs2_extent_map_insert_rec(inode, &rec);
}
if (extent_flags)
@@ -478,7 +608,6 @@ int ocfs2_get_clusters(struct inode *inode, u32 v_cluster,
out:
brelse(di_bh);
- brelse(eb_bh);
return ret;
}
@@ -521,3 +650,114 @@ int ocfs2_extent_map_get_blocks(struct inode *inode, u64 v_blkno, u64 *p_blkno,
out:
return ret;
}
+
+static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
+ struct fiemap_extent_info *fieinfo,
+ u64 map_start)
+{
+ int ret;
+ unsigned int id_count;
+ struct ocfs2_dinode *di;
+ u64 phys;
+ u32 flags = FIEMAP_EXTENT_DATA_INLINE|FIEMAP_EXTENT_LAST;
+ struct ocfs2_inode_info *oi = OCFS2_I(inode);
+
+ di = (struct ocfs2_dinode *)di_bh->b_data;
+ id_count = le16_to_cpu(di->id2.i_data.id_count);
+
+ if (map_start < id_count) {
+ phys = oi->ip_blkno << inode->i_sb->s_blocksize_bits;
+ phys += offsetof(struct ocfs2_dinode, id2.i_data.id_data);
+
+ ret = fiemap_fill_next_extent(fieinfo, 0, phys, id_count,
+ flags);
+ if (ret < 0)
+ return ret;
+ }
+
+ return 0;
+}
+
+#define OCFS2_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC)
+
+int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 map_start, u64 map_len)
+{
+ int ret, is_last;
+ u32 mapping_end, cpos;
+ unsigned int hole_size;
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ u64 len_bytes, phys_bytes, virt_bytes;
+ struct buffer_head *di_bh = NULL;
+ struct ocfs2_extent_rec rec;
+
+ ret = fiemap_check_flags(fieinfo, OCFS2_FIEMAP_FLAGS);
+ if (ret)
+ return ret;
+
+ ret = ocfs2_inode_lock(inode, &di_bh, 0);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ down_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+ /*
+ * Handle inline-data separately.
+ */
+ if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+ ret = ocfs2_fiemap_inline(inode, di_bh, fieinfo, map_start);
+ goto out_unlock;
+ }
+
+ cpos = map_start >> osb->s_clustersize_bits;
+ mapping_end = ocfs2_clusters_for_bytes(inode->i_sb,
+ map_start + map_len);
+ mapping_end -= cpos;
+ is_last = 0;
+ while (cpos < mapping_end && !is_last) {
+ u32 fe_flags;
+
+ ret = ocfs2_get_clusters_nocache(inode, di_bh, cpos,
+ &hole_size, &rec, &is_last);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ if (rec.e_blkno == 0ULL) {
+ cpos += hole_size;
+ continue;
+ }
+
+ fe_flags = 0;
+ if (rec.e_flags & OCFS2_EXT_UNWRITTEN)
+ fe_flags |= FIEMAP_EXTENT_UNWRITTEN;
+ if (is_last)
+ fe_flags |= FIEMAP_EXTENT_LAST;
+ len_bytes = (u64)le16_to_cpu(rec.e_leaf_clusters) << osb->s_clustersize_bits;
+ phys_bytes = le64_to_cpu(rec.e_blkno) << osb->sb->s_blocksize_bits;
+ virt_bytes = (u64)le32_to_cpu(rec.e_cpos) << osb->s_clustersize_bits;
+
+ ret = fiemap_fill_next_extent(fieinfo, virt_bytes, phys_bytes,
+ len_bytes, fe_flags);
+ if (ret)
+ break;
+
+ cpos = le32_to_cpu(rec.e_cpos)+ le16_to_cpu(rec.e_leaf_clusters);
+ }
+
+ if (ret > 0)
+ ret = 0;
+
+out_unlock:
+ brelse(di_bh);
+
+ up_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+ ocfs2_inode_unlock(inode, 0);
+out:
+
+ return ret;
+}
diff --git a/fs/ocfs2/extent_map.h b/fs/ocfs2/extent_map.h
index de91e3e..1b97490 100644
--- a/fs/ocfs2/extent_map.h
+++ b/fs/ocfs2/extent_map.h
@@ -50,4 +50,7 @@ int ocfs2_get_clusters(struct inode *inode, u32 v_cluster, u32 *p_cluster,
int ocfs2_extent_map_get_blocks(struct inode *inode, u64 v_blkno, u64 *p_blkno,
u64 *ret_count, unsigned int *extent_flags);
+int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 map_start, u64 map_len);
+
#endif /* _EXTENT_MAP_H */
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index ec2ed15..ed38796 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2228,6 +2228,7 @@ const struct inode_operations ocfs2_file_iops = {
.getattr = ocfs2_getattr,
.permission = ocfs2_permission,
.fallocate = ocfs2_fallocate,
+ .fiemap = ocfs2_fiemap,
};
const struct inode_operations ocfs2_special_file_iops = {
--
1.5.6.1.205.ge2c7.dirty
^ permalink raw reply related [flat|nested] 13+ messages in thread
* [PATCH 3/4] generic block based fiemap implementation
2008-10-07 1:06 ` [PATCH 2/4] ocfs2: fiemap support Theodore Ts'o
@ 2008-10-07 1:06 ` Theodore Ts'o
2008-10-07 1:06 ` [PATCH 4/4] Hook ext4 to the vfs fiemap interface Theodore Ts'o
0 siblings, 1 reply; 13+ messages in thread
From: Theodore Ts'o @ 2008-10-07 1:06 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Josef Bacik, Mark Fasheh, Theodore Ts'o
From: Josef Bacik <jbacik@redhat.com>
Any block based fs (this patch includes ext3) just has to declare its own
fiemap() function and then call this generic function with its own
get_block_t. This works well for block based filesystems that will map
multiple contiguous blocks at one time, but will work for filesystems that
only map one block at a time, you will just end up with an "extent" for each
block. One gotcha is this will not play nicely where there is hole+data
after the EOF. This function will assume its hit the end of the data as soon
as it hits a hole after the EOF, so if there is any data past that it will
not pick that up. AFAIK no block based fs does this anyway, but its in the
comments of the function anyway just in case.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: linux-fsdevel@vger.kernel.org
---
fs/ext2/ext2.h | 2 +
fs/ext2/file.c | 1 +
fs/ext2/inode.c | 8 +++
fs/ext3/file.c | 1 +
fs/ext3/inode.c | 8 +++
fs/ioctl.c | 118 +++++++++++++++++++++++++++++++++++++++++++++++
include/linux/ext3_fs.h | 2 +
include/linux/fs.h | 3 +
8 files changed, 143 insertions(+), 0 deletions(-)
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 47d88da..bae998c 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -133,6 +133,8 @@ extern void ext2_truncate (struct inode *);
extern int ext2_setattr (struct dentry *, struct iattr *);
extern void ext2_set_inode_flags(struct inode *inode);
extern void ext2_get_inode_flags(struct ext2_inode_info *);
+extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len);
int __ext2_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata);
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 5f2fa9c..45ed071 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -86,4 +86,5 @@ const struct inode_operations ext2_file_inode_operations = {
#endif
.setattr = ext2_setattr,
.permission = ext2_permission,
+ .fiemap = ext2_fiemap,
};
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 991d6df..7658b33 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -31,6 +31,7 @@
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
+#include <linux/fiemap.h>
#include "ext2.h"
#include "acl.h"
#include "xip.h"
@@ -704,6 +705,13 @@ int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_
}
+int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ return generic_block_fiemap(inode, fieinfo, start, len,
+ ext2_get_block);
+}
+
static int ext2_writepage(struct page *page, struct writeback_control *wbc)
{
return block_write_full_page(page, ext2_get_block, wbc);
diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index acc4913..3be1e06 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -134,5 +134,6 @@ const struct inode_operations ext3_file_inode_operations = {
.removexattr = generic_removexattr,
#endif
.permission = ext3_permission,
+ .fiemap = ext3_fiemap,
};
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 507d868..ebfec4d 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -36,6 +36,7 @@
#include <linux/mpage.h>
#include <linux/uio.h>
#include <linux/bio.h>
+#include <linux/fiemap.h>
#include "xattr.h"
#include "acl.h"
@@ -981,6 +982,13 @@ out:
return ret;
}
+int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ return generic_block_fiemap(inode, fieinfo, start, len,
+ ext3_get_block);
+}
+
/*
* `handle' can be NULL if create is zero
*/
diff --git a/fs/ioctl.c b/fs/ioctl.c
index b759cc2..f364f33 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -13,6 +13,8 @@
#include <linux/security.h>
#include <linux/module.h>
#include <linux/uaccess.h>
+#include <linux/writeback.h>
+#include <linux/buffer_head.h>
#include <asm/ioctls.h>
@@ -224,6 +226,122 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg)
return error;
}
+#define blk_to_logical(inode, blk) (blk << (inode)->i_blkbits)
+#define logical_to_blk(inode, offset) (offset >> (inode)->i_blkbits);
+
+/*
+ * @inode - the inode to map
+ * @arg - the pointer to userspace where we copy everything to
+ * @get_block - the fs's get_block function
+ *
+ * This does FIEMAP for block based inodes. Basically it will just loop
+ * through get_block until we hit the number of extents we want to map, or we
+ * go past the end of the file and hit a hole.
+ *
+ * If it is possible to have data blocks beyond a hole past @inode->i_size, then
+ * please do not use this function, it will stop at the first unmapped block
+ * beyond i_size
+ */
+int generic_block_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo, u64 start,
+ u64 len, get_block_t *get_block)
+{
+ struct buffer_head tmp;
+ unsigned int start_blk;
+ long long length = 0, map_len = 0;
+ u64 logical = 0, phys = 0, size = 0;
+ u32 flags = FIEMAP_EXTENT_MERGED;
+ int ret = 0;
+
+ if ((ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC)))
+ return ret;
+
+ start_blk = logical_to_blk(inode, start);
+
+ /* guard against change */
+ mutex_lock(&inode->i_mutex);
+
+ length = (long long)min_t(u64, len, i_size_read(inode));
+ map_len = length;
+
+ do {
+ /*
+ * we set b_size to the total size we want so it will map as
+ * many contiguous blocks as possible at once
+ */
+ memset(&tmp, 0, sizeof(struct buffer_head));
+ tmp.b_size = map_len;
+
+ ret = get_block(inode, start_blk, &tmp, 0);
+ if (ret)
+ break;
+
+ /* HOLE */
+ if (!buffer_mapped(&tmp)) {
+ /*
+ * first hole after going past the EOF, this is our
+ * last extent
+ */
+ if (length <= 0) {
+ flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size,
+ flags);
+ break;
+ }
+
+ length -= blk_to_logical(inode, 1);
+
+ /* if we have holes up to/past EOF then we're done */
+ if (length <= 0)
+ break;
+
+ start_blk++;
+ } else {
+ if (length <= 0 && size) {
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size,
+ flags);
+ if (ret)
+ break;
+ }
+
+ logical = blk_to_logical(inode, start_blk);
+ phys = blk_to_logical(inode, tmp.b_blocknr);
+ size = tmp.b_size;
+ flags = FIEMAP_EXTENT_MERGED;
+
+ length -= tmp.b_size;
+ start_blk += logical_to_blk(inode, size);
+
+ /*
+ * if we are past the EOF we need to loop again to see
+ * if there is a hole so we can mark this extent as the
+ * last one, and if not keep mapping things until we
+ * find a hole, or we run out of slots in the extent
+ * array
+ */
+ if (length <= 0)
+ continue;
+
+ ret = fiemap_fill_next_extent(fieinfo, logical, phys,
+ size, flags);
+ if (ret)
+ break;
+ }
+ cond_resched();
+ } while (1);
+
+ mutex_unlock(&inode->i_mutex);
+
+ /* if ret is 1 then we just hit the end of the extent array */
+ if (ret == 1)
+ ret = 0;
+
+ return ret;
+}
+EXPORT_SYMBOL(generic_block_fiemap);
+
static int file_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
{
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 80171ee..8120fa1 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -837,6 +837,8 @@ extern void ext3_truncate (struct inode *);
extern void ext3_set_inode_flags(struct inode *);
extern void ext3_get_inode_flags(struct ext3_inode_info *);
extern void ext3_set_aops(struct inode *inode);
+extern int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len);
/* ioctl.c */
extern int ext3_ioctl (struct inode *, struct file *, unsigned int,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 194fb23..385c9a1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1998,6 +1998,9 @@ extern int vfs_fstat(unsigned int, struct kstat *);
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
unsigned long arg);
+extern int generic_block_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo, u64 start,
+ u64 len, get_block_t *get_block);
extern void get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
--
1.5.6.1.205.ge2c7.dirty
^ permalink raw reply related [flat|nested] 13+ messages in thread
* [PATCH 4/4] Hook ext4 to the vfs fiemap interface.
2008-10-07 1:06 ` [PATCH 3/4] generic block based fiemap implementation Theodore Ts'o
@ 2008-10-07 1:06 ` Theodore Ts'o
0 siblings, 0 replies; 13+ messages in thread
From: Theodore Ts'o @ 2008-10-07 1:06 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Eric Sandeen, Theodore Ts'o, linux-ext4
From: Eric Sandeen <sandeen@redhat.com>
ext4_ext_walk_space() was reinstated to be used for iterating over file
extents with a callback; it is used by the ext4 fiemap implementation.
Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: linux-ext4@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org
---
fs/ext4/ext4.h | 2 +
fs/ext4/ext4_extents.h | 15 +++
fs/ext4/extents.c | 248 ++++++++++++++++++++++++++++++++++++++++++++++++
fs/ext4/file.c | 4 +
4 files changed, 269 insertions(+), 0 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index c50c04c..f46a513 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1067,6 +1067,8 @@ struct buffer_head *ext4_getblk(handle_t *, struct inode *,
ext4_lblk_t, int, int *);
struct buffer_head *ext4_bread(handle_t *, struct inode *,
ext4_lblk_t, int, int *);
+int ext4_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create);
int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
ext4_lblk_t iblock, unsigned long maxblocks,
struct buffer_head *bh_result,
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index d33dc56..bec7ce5 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -124,6 +124,19 @@ struct ext4_ext_path {
#define EXT4_EXT_CACHE_GAP 1
#define EXT4_EXT_CACHE_EXTENT 2
+/*
+ * to be called by ext4_ext_walk_space()
+ * negative retcode - error
+ * positive retcode - signal for ext4_ext_walk_space(), see below
+ * callback must return valid extent (passed or newly created)
+ */
+typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *,
+ struct ext4_ext_cache *,
+ struct ext4_extent *, void *);
+
+#define EXT_CONTINUE 0
+#define EXT_BREAK 1
+#define EXT_REPEAT 2
#define EXT_MAX_BLOCK 0xffffffff
@@ -224,6 +237,8 @@ extern int ext4_ext_try_to_merge(struct inode *inode,
struct ext4_extent *);
extern unsigned int ext4_ext_check_overlap(struct inode *, struct ext4_extent *, struct ext4_ext_path *);
extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *);
+extern int ext4_ext_walk_space(struct inode *, ext4_lblk_t, ext4_lblk_t,
+ ext_prepare_callback, void *);
extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
struct ext4_ext_path *);
extern int ext4_ext_search_left(struct inode *, struct ext4_ext_path *,
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index c8f81f2..ea2ce3c 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -40,6 +40,7 @@
#include <linux/slab.h>
#include <linux/falloc.h>
#include <asm/uaccess.h>
+#include <linux/fiemap.h>
#include "ext4_jbd2.h"
#include "ext4_extents.h"
@@ -1626,6 +1627,113 @@ cleanup:
return err;
}
+int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
+ ext4_lblk_t num, ext_prepare_callback func,
+ void *cbdata)
+{
+ struct ext4_ext_path *path = NULL;
+ struct ext4_ext_cache cbex;
+ struct ext4_extent *ex;
+ ext4_lblk_t next, start = 0, end = 0;
+ ext4_lblk_t last = block + num;
+ int depth, exists, err = 0;
+
+ BUG_ON(func == NULL);
+ BUG_ON(inode == NULL);
+
+ while (block < last && block != EXT_MAX_BLOCK) {
+ num = last - block;
+ /* find extent for this block */
+ path = ext4_ext_find_extent(inode, block, path);
+ if (IS_ERR(path)) {
+ err = PTR_ERR(path);
+ path = NULL;
+ break;
+ }
+
+ depth = ext_depth(inode);
+ BUG_ON(path[depth].p_hdr == NULL);
+ ex = path[depth].p_ext;
+ next = ext4_ext_next_allocated_block(path);
+
+ exists = 0;
+ if (!ex) {
+ /* there is no extent yet, so try to allocate
+ * all requested space */
+ start = block;
+ end = block + num;
+ } else if (le32_to_cpu(ex->ee_block) > block) {
+ /* need to allocate space before found extent */
+ start = block;
+ end = le32_to_cpu(ex->ee_block);
+ if (block + num < end)
+ end = block + num;
+ } else if (block >= le32_to_cpu(ex->ee_block)
+ + ext4_ext_get_actual_len(ex)) {
+ /* need to allocate space after found extent */
+ start = block;
+ end = block + num;
+ if (end >= next)
+ end = next;
+ } else if (block >= le32_to_cpu(ex->ee_block)) {
+ /*
+ * some part of requested space is covered
+ * by found extent
+ */
+ start = block;
+ end = le32_to_cpu(ex->ee_block)
+ + ext4_ext_get_actual_len(ex);
+ if (block + num < end)
+ end = block + num;
+ exists = 1;
+ } else {
+ BUG();
+ }
+ BUG_ON(end <= start);
+
+ if (!exists) {
+ cbex.ec_block = start;
+ cbex.ec_len = end - start;
+ cbex.ec_start = 0;
+ cbex.ec_type = EXT4_EXT_CACHE_GAP;
+ } else {
+ cbex.ec_block = le32_to_cpu(ex->ee_block);
+ cbex.ec_len = ext4_ext_get_actual_len(ex);
+ cbex.ec_start = ext_pblock(ex);
+ cbex.ec_type = EXT4_EXT_CACHE_EXTENT;
+ }
+
+ BUG_ON(cbex.ec_len == 0);
+ err = func(inode, path, &cbex, ex, cbdata);
+ ext4_ext_drop_refs(path);
+
+ if (err < 0)
+ break;
+
+ if (err == EXT_REPEAT)
+ continue;
+ else if (err == EXT_BREAK) {
+ err = 0;
+ break;
+ }
+
+ if (ext_depth(inode) != depth) {
+ /* depth was changed. we have to realloc path */
+ kfree(path);
+ path = NULL;
+ }
+
+ block = cbex.ec_block + cbex.ec_len;
+ }
+
+ if (path) {
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ }
+
+ return err;
+}
+
static void
ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block,
__u32 len, ext4_fsblk_t start, int type)
@@ -2971,3 +3079,143 @@ retry:
mutex_unlock(&inode->i_mutex);
return ret > 0 ? ret2 : ret;
}
+
+/*
+ * Callback function called for each extent to gather FIEMAP information.
+ */
+int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
+ struct ext4_ext_cache *newex, struct ext4_extent *ex,
+ void *data)
+{
+ struct fiemap_extent_info *fieinfo = data;
+ unsigned long blksize_bits = inode->i_sb->s_blocksize_bits;
+ __u64 logical;
+ __u64 physical;
+ __u64 length;
+ __u32 flags = 0;
+ int error;
+
+ logical = (__u64)newex->ec_block << blksize_bits;
+
+ if (newex->ec_type == EXT4_EXT_CACHE_GAP) {
+ pgoff_t offset;
+ struct page *page;
+ struct buffer_head *bh = NULL;
+
+ offset = logical >> PAGE_SHIFT;
+ page = find_get_page(inode->i_mapping, offset);
+ if (!page || !page_has_buffers(page))
+ return EXT_CONTINUE;
+
+ bh = page_buffers(page);
+
+ if (!bh)
+ return EXT_CONTINUE;
+
+ if (buffer_delay(bh)) {
+ flags |= FIEMAP_EXTENT_DELALLOC;
+ page_cache_release(page);
+ } else {
+ page_cache_release(page);
+ return EXT_CONTINUE;
+ }
+ }
+
+ physical = (__u64)newex->ec_start << blksize_bits;
+ length = (__u64)newex->ec_len << blksize_bits;
+
+ if (ex && ext4_ext_is_uninitialized(ex))
+ flags |= FIEMAP_EXTENT_UNWRITTEN;
+
+ /*
+ * If this extent reaches EXT_MAX_BLOCK, it must be last.
+ *
+ * Or if ext4_ext_next_allocated_block is EXT_MAX_BLOCK,
+ * this also indicates no more allocated blocks.
+ *
+ * XXX this might miss a single-block extent at EXT_MAX_BLOCK
+ */
+ if (logical + length - 1 == EXT_MAX_BLOCK ||
+ ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK)
+ flags |= FIEMAP_EXTENT_LAST;
+
+ error = fiemap_fill_next_extent(fieinfo, logical, physical,
+ length, flags);
+ if (error < 0)
+ return error;
+ if (error == 1)
+ return EXT_BREAK;
+
+ return EXT_CONTINUE;
+}
+
+/* fiemap flags we can handle specified here */
+#define EXT4_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
+
+int ext4_xattr_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo)
+{
+ __u64 physical = 0;
+ __u64 length;
+ __u32 flags = FIEMAP_EXTENT_LAST;
+ int blockbits = inode->i_sb->s_blocksize_bits;
+ int error = 0;
+
+ /* in-inode? */
+ if (EXT4_I(inode)->i_state & EXT4_STATE_XATTR) {
+ struct ext4_iloc iloc;
+ int offset; /* offset of xattr in inode */
+
+ error = ext4_get_inode_loc(inode, &iloc);
+ if (error)
+ return error;
+ physical = iloc.bh->b_blocknr << blockbits;
+ offset = EXT4_GOOD_OLD_INODE_SIZE +
+ EXT4_I(inode)->i_extra_isize;
+ physical += offset;
+ length = EXT4_SB(inode->i_sb)->s_inode_size - offset;
+ flags |= FIEMAP_EXTENT_DATA_INLINE;
+ } else { /* external block */
+ physical = EXT4_I(inode)->i_file_acl << blockbits;
+ length = inode->i_sb->s_blocksize;
+ }
+
+ if (physical)
+ error = fiemap_fill_next_extent(fieinfo, 0, physical,
+ length, flags);
+ return (error < 0 ? error : 0);
+}
+
+int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ __u64 start, __u64 len)
+{
+ ext4_lblk_t start_blk;
+ ext4_lblk_t len_blks;
+ int error = 0;
+
+ /* fallback to generic here if not in extents fmt */
+ if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ return generic_block_fiemap(inode, fieinfo, start, len,
+ ext4_get_block);
+
+ if (fiemap_check_flags(fieinfo, EXT4_FIEMAP_FLAGS))
+ return -EBADR;
+
+ if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
+ error = ext4_xattr_fiemap(inode, fieinfo);
+ } else {
+ start_blk = start >> inode->i_sb->s_blocksize_bits;
+ len_blks = len >> inode->i_sb->s_blocksize_bits;
+
+ /*
+ * Walk the extent tree gathering extent information.
+ * ext4_ext_fiemap_cb will push extents back to user.
+ */
+ down_write(&EXT4_I(inode)->i_data_sem);
+ error = ext4_ext_walk_space(inode, start_blk, len_blks,
+ ext4_ext_fiemap_cb, fieinfo);
+ up_write(&EXT4_I(inode)->i_data_sem);
+ }
+
+ return error;
+}
+
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 62796b7..6d5be15 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -140,6 +140,9 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
return 0;
}
+extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ __u64 start, __u64 len);
+
const struct file_operations ext4_file_operations = {
.llseek = generic_file_llseek,
.read = do_sync_read,
@@ -170,5 +173,6 @@ const struct inode_operations ext4_file_inode_operations = {
#endif
.permission = ext4_permission,
.fallocate = ext4_fallocate,
+ .fiemap = ext4_fiemap,
};
--
1.5.6.1.205.ge2c7.dirty
^ permalink raw reply related [flat|nested] 13+ messages in thread
* Re: [PATCH 1/4] vfs: vfs-level fiemap interface
[not found] ` <1223341581-13802-2-git-send-email-tytso-3s7WtUTddSA@public.gmane.org>
@ 2008-10-07 1:09 ` Theodore Tso
0 siblings, 0 replies; 13+ messages in thread
From: Theodore Tso @ 2008-10-07 1:09 UTC (permalink / raw)
To: linux-fsdevel-u79uwXL29TY76Z2rM5mHXA
Cc: Mark Fasheh, Michael Kerrisk, linux-api-u79uwXL29TY76Z2rM5mHXA
Sorry, I sent the wrong version of the patch; here's the correct
updated one that has an additional typographical fix in the
description of the FIEMAP_EXTENT_NO_UNMOUNTED_IO flag.
- Ted
vfs: vfs-level fiemap interface
From: Mark Fasheh <mfasheh-IBi9RG/b67k@public.gmane.org>
Basic vfs-level fiemap infrastructure, which sets up a new ->fiemap
inode operation.
Userspace can get extent information on a file via fiemap ioctl. As input,
the fiemap ioctl takes a struct fiemap which includes an array of struct
fiemap_extent (fm_extents). Size of the extent array is passed as
fm_extent_count and number of extents returned will be written into
fm_mapped_extents. Offset and length fields on the fiemap structure
(fm_start, fm_length) describe a logical range which will be searched for
extents. All extents returned will at least partially contain this range.
The actual extent offsets and ranges returned will be unmodified from their
offset and range on-disk.
The fiemap ioctl returns '0' on success. On error, -1 is returned and errno
is set. If errno is equal to EBADR, then fm_flags will contain those flags
which were passed in which the kernel did not understand. On all other
errors, the contents of fm_extents is undefined.
As fiemap evolved, there have been many authors of the vfs patch. As far as
I can tell, the list includes:
Kalpak Shah <kalpak.shah-xsfywfwIY+M@public.gmane.org>
Andreas Dilger <adilger-xsfywfwIY+M@public.gmane.org>
Eric Sandeen <sandeen-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Mark Fasheh <mfasheh-IBi9RG/b67k@public.gmane.org>
Signed-off-by: Mark Fasheh <mfasheh-IBi9RG/b67k@public.gmane.org>
Signed-off-by: "Theodore Ts'o" <tytso-3s7WtUTddSA@public.gmane.org>
Cc: Michael Kerrisk <mtk.manpages-gM/Ye1E23mwN+BqQ9rBEUg@public.gmane.org>
Cc: linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Cc: linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
diff --git a/Documentation/filesystems/fiemap.txt b/Documentation/filesystems/fiemap.txt
new file mode 100644
index 0000000..0945d96
--- /dev/null
+++ b/Documentation/filesystems/fiemap.txt
@@ -0,0 +1,221 @@
+============
+Fiemap Ioctl
+============
+
+The fiemap ioctl is an efficient method for userspace to get file
+extent mappings. Instead of block-by-block mapping (such as bmap), fiemap
+returns a list of extents.
+
+
+Request Basics
+--------------
+
+A fiemap request is encoded within struct fiemap:
+
+struct fiemap {
+ __u64 fm_start; /* logical offset (inclusive) at
+ * which to start mapping (in) */
+ __u64 fm_length; /* logical length of mapping which
+ * userspace cares about (in) */
+ __u32 fm_flags; /* FIEMAP_FLAG_* flags for request (in/out) */
+ __u32 fm_mapped_extents; /* number of extents that were
+ * mapped (out) */
+ __u32 fm_extent_count; /* size of fm_extents array (in) */
+ __u32 fm_reserved;
+ struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */
+};
+
+
+fm_start, and fm_length specify the logical range within the file
+which the process would like mappings for. Extents returned mirror
+those on disk - that is, the logical offset of the 1st returned extent
+may start before fm_start, and the range covered by the last returned
+extent may end after fm_length. All offsets and lengths are in bytes.
+
+Certain flags to modify the way in which mappings are looked up can be
+set in fm_flags. If the kernel doesn't understand some particular
+flags, it will return EBADR and the contents of fm_flags will contain
+the set of flags which caused the error. If the kernel is compatible
+with all flags passed, the contents of fm_flags will be unmodified.
+It is up to userspace to determine whether rejection of a particular
+flag is fatal to it's operation. This scheme is intended to allow the
+fiemap interface to grow in the future but without losing
+compatibility with old software.
+
+fm_extent_count specifies the number of elements in the fm_extents[] array
+that can be used to return extents. If fm_extent_count is zero, then the
+fm_extents[] array is ignored (no extents will be returned), and the
+fm_mapped_extents count will hold the number of extents needed in
+fm_extents[] to hold the file's current mapping. Note that there is
+nothing to prevent the file from changing between calls to FIEMAP.
+
+The following flags can be set in fm_flags:
+
+* FIEMAP_FLAG_SYNC
+If this flag is set, the kernel will sync the file before mapping extents.
+
+* FIEMAP_FLAG_XATTR
+If this flag is set, the extents returned will describe the inodes
+extended attribute lookup tree, instead of it's data tree.
+
+
+Extent Mapping
+--------------
+
+Extent information is returned within the embedded fm_extents array
+which userspace must allocate along with the fiemap structure. The
+number of elements in the fiemap_extents[] array should be passed via
+fm_extent_count. The number of extents mapped by kernel will be
+returned via fm_mapped_extents. If the number of fiemap_extents
+allocated is less than would be required to map the requested range,
+the maximum number of extents that can be mapped in the fm_extent[]
+array will be returned and fm_mapped_extents will be equal to
+fm_extent_count. In that case, the last extent in the array will not
+complete the requested range and will not have the FIEMAP_EXTENT_LAST
+flag set (see the next section on extent flags).
+
+Each extent is described by a single fiemap_extent structure as
+returned in fm_extents.
+
+struct fiemap_extent {
+ __u64 fe_logical; /* logical offset in bytes for the start of
+ * the extent */
+ __u64 fe_physical; /* physical offset in bytes for the start
+ * of the extent */
+ __u64 fe_length; /* length in bytes for the extent */
+ __u64 fe_reserved64[2];
+ __u32 fe_flags; /* FIEMAP_EXTENT_* flags for this extent */
+ __u32 fe_reserved[3];
+};
+
+All offsets and lengths are in bytes and mirror those on disk. It is valid
+for an extents logical offset to start before the request or it's logical
+length to extend past the request. Unless FIEMAP_EXTENT_NOT_ALIGNED is
+returned, fe_logical, fe_physical, and fe_length will be aligned to the
+block size of the file system. With the exception of extents flagged as
+FIEMAP_EXTENT_MERGED, adjacent extents will not be merged.
+
+The fe_flags field contains flags which describe the extent returned.
+A special flag, FIEMAP_EXTENT_LAST is always set on the last extent in
+the file so that the process making fiemap calls can determine when no
+more extents are available, without having to call the ioctl again.
+
+Some flags are intentionally vague and will always be set in the
+presence of other more specific flags. This way a program looking for
+a general property does not have to know all existing and future flags
+which imply that property.
+
+For example, if FIEMAP_EXTENT_DATA_INLINE or FIEMAP_EXTENT_DATA_TAIL
+are set, FIEMAP_EXTENT_NOT_ALIGNED will also be set. A program looking
+for inline or tail-packed data can key on the specific flag. Software
+which simply cares not to try operating on non-aligned extents
+however, can just key on FIEMAP_EXTENT_NOT_ALIGNED, and not have to
+worry about all present and future flags which might imply unaligned
+data. Note that the opposite is not true - it would be valid for
+FIEMAP_EXTENT_NOT_ALIGNED to appear alone.
+
+* FIEMAP_EXTENT_LAST
+This is the last extent in the file. A mapping attempt past this
+extent will return nothing.
+
+* FIEMAP_EXTENT_UNKNOWN
+The location of this extent is currently unknown. This may indicate
+the data is stored on an inaccessible volume or that no storage has
+been allocated for the file yet.
+
+* FIEMAP_EXTENT_DELALLOC
+ - This will also set FIEMAP_EXTENT_UNKNOWN.
+Delayed allocation - while there is data for this extent, it's
+physical location has not been allocated yet.
+
+* FIEMAP_EXTENT_NO_UNMOUNTED_IO
+Accessing the data in this extent via I/O to the block device while the
+filesystem is unmounted is illegal or will have undefined results. This
+may be because the data is somehow encrypted or compressed by the filesystem.
+Note that accessing the data using the information returned by the
+FIEMAP interface while the filesystem is mounted is *always* undefined
+should not be attempted by user applications.
+
+* FIEMAP_EXTENT_DATA_ENCRYPTED
+ - This will also set FIEMAP_EXTENT_NO_UNMOUNTED_IO
+The data in this extent has been encrypted by the file system.
+
+* FIEMAP_EXTENT_NOT_ALIGNED
+Extent offsets and length are not guaranteed to be block aligned.
+
+* FIEMAP_EXTENT_DATA_INLINE
+ This will also set FIEMAP_EXTENT_NOT_ALIGNED
+Data is located within a meta data block.
+
+* FIEMAP_EXTENT_DATA_TAIL
+ This will also set FIEMAP_EXTENT_NOT_ALIGNED
+Data is packed into a block with data from other files.
+
+* FIEMAP_EXTENT_UNWRITTEN
+Unwritten extent - the extent is allocated but it's data has not been
+initialized. This indicates the extent's data will be all zero if read
+through the filesystem but the contents are undefined if read directly from
+the device.
+
+* FIEMAP_EXTENT_MERGED
+This will be set when a file does not support extents, i.e., it uses a block
+based addressing scheme. Since returning an extent for each block back to
+userspace would be highly inefficient, the kernel will try to merge most
+adjacent blocks into 'extents'.
+
+
+VFS -> File System Implementation
+---------------------------------
+
+File systems wishing to support fiemap must implement a ->fiemap callback on
+their inode_operations structure. The fs ->fiemap call is responsible for
+defining it's set of supported fiemap flags, and calling a helper function on
+each discovered extent:
+
+struct inode_operations {
+ ...
+
+ int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
+ u64 len);
+
+->fiemap is passed struct fiemap_extent_info which describes the
+fiemap request:
+
+struct fiemap_extent_info {
+ unsigned int fi_flags; /* Flags as passed from user */
+ unsigned int fi_extents_mapped; /* Number of mapped extents */
+ unsigned int fi_extents_max; /* Size of fiemap_extent array */
+ struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent array */
+};
+
+It is intended that the file system should not need to access any of this
+structure directly.
+
+
+Flag checking should be done at the beginning of the ->fiemap callback via the
+fiemap_check_flags() helper:
+
+int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
+
+The struct fieinfo should be passed in as recieved from ioctl_fiemap(). The
+set of fiemap flags which the fs understands should be passed via fs_flags. If
+fiemap_check_flags finds invalid user flags, it will place the bad values in
+fieinfo->fi_flags and return -EBADR. If the file system gets -EBADR, from
+fiemap_check_flags(), it should immediately exit, returning that error back to
+ioctl_fiemap().
+
+
+For each extent in the request range, the file system should call
+the helper function, fiemap_fill_next_extent():
+
+int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
+ u64 phys, u64 len, u32 flags, u32 dev);
+
+fiemap_fill_next_extent() will use the passed values to populate the
+next free extent in the fm_extents array. 'General' extent flags will
+automatically be set from specific flags on behalf of the calling file
+system so that the userspace API is not broken.
+
+fiemap_fill_next_extent() returns 0 on success, and 1 when the
+user-supplied fm_extents array is full. If an error is encountered
+while copying the extent to user memory, -EFAULT will be returned.
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 7db32b3..1f3a658 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -16,6 +16,9 @@
#include <asm/ioctls.h>
+/* So that the fiemap access checks can't overflow on 32 bit machines. */
+#define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent))
+
/**
* vfs_ioctl - call filesystem specific ioctl methods
* @filp: open file to invoke ioctl method on
@@ -71,6 +74,156 @@ static int ioctl_fibmap(struct file *filp, int __user *p)
return put_user(res, p);
}
+/**
+ * fiemap_fill_next_extent - Fiemap helper function
+ * @fieinfo: Fiemap context passed into ->fiemap
+ * @logical: Extent logical start offset, in bytes
+ * @phys: Extent physical start offset, in bytes
+ * @len: Extent length, in bytes
+ * @flags: FIEMAP_EXTENT flags that describe this extent
+ *
+ * Called from file system ->fiemap callback. Will populate extent
+ * info as passed in via arguments and copy to user memory. On
+ * success, extent count on fieinfo is incremented.
+ *
+ * Returns 0 on success, -errno on error, 1 if this was the last
+ * extent that will fit in user array.
+ */
+#define SET_UNKNOWN_FLAGS (FIEMAP_EXTENT_DELALLOC)
+#define SET_NO_UNMOUNTED_IO_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED)
+#define SET_NOT_ALIGNED_FLAGS (FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE)
+int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical,
+ u64 phys, u64 len, u32 flags)
+{
+ struct fiemap_extent extent;
+ struct fiemap_extent *dest = fieinfo->fi_extents_start;
+
+ /* only count the extents */
+ if (fieinfo->fi_extents_max == 0) {
+ fieinfo->fi_extents_mapped++;
+ return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
+ }
+
+ if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max)
+ return 1;
+
+ if (flags & SET_UNKNOWN_FLAGS)
+ flags |= FIEMAP_EXTENT_UNKNOWN;
+ if (flags & SET_NO_UNMOUNTED_IO_FLAGS)
+ flags |= FIEMAP_EXTENT_NO_UNMOUNTED_IO;
+ if (flags & SET_NOT_ALIGNED_FLAGS)
+ flags |= FIEMAP_EXTENT_NOT_ALIGNED;
+
+ memset(&extent, 0, sizeof(extent));
+ extent.fe_logical = logical;
+ extent.fe_physical = phys;
+ extent.fe_length = len;
+ extent.fe_flags = flags;
+
+ dest += fieinfo->fi_extents_mapped;
+ if (copy_to_user(dest, &extent, sizeof(extent)))
+ return -EFAULT;
+
+ fieinfo->fi_extents_mapped++;
+ if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max)
+ return 1;
+ return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
+}
+EXPORT_SYMBOL(fiemap_fill_next_extent);
+
+/**
+ * fiemap_check_flags - check validity of requested flags for fiemap
+ * @fieinfo: Fiemap context passed into ->fiemap
+ * @fs_flags: Set of fiemap flags that the file system understands
+ *
+ * Called from file system ->fiemap callback. This will compute the
+ * intersection of valid fiemap flags and those that the fs supports. That
+ * value is then compared against the user supplied flags. In case of bad user
+ * flags, the invalid values will be written into the fieinfo structure, and
+ * -EBADR is returned, which tells ioctl_fiemap() to return those values to
+ * userspace. For this reason, a return code of -EBADR should be preserved.
+ *
+ * Returns 0 on success, -EBADR on bad flags.
+ */
+int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags)
+{
+ u32 incompat_flags;
+
+ incompat_flags = fieinfo->fi_flags & ~(FIEMAP_FLAGS_COMPAT & fs_flags);
+ if (incompat_flags) {
+ fieinfo->fi_flags = incompat_flags;
+ return -EBADR;
+ }
+ return 0;
+}
+EXPORT_SYMBOL(fiemap_check_flags);
+
+static int fiemap_check_ranges(struct super_block *sb,
+ u64 start, u64 len, u64 *new_len)
+{
+ *new_len = len;
+
+ if (len == 0)
+ return -EINVAL;
+
+ if (start > sb->s_maxbytes)
+ return -EFBIG;
+
+ /*
+ * Shrink request scope to what the fs can actually handle.
+ */
+ if ((len > sb->s_maxbytes) ||
+ (sb->s_maxbytes - len) < start)
+ *new_len = sb->s_maxbytes - start;
+
+ return 0;
+}
+
+static int ioctl_fiemap(struct file *filp, unsigned long arg)
+{
+ struct fiemap fiemap;
+ struct fiemap_extent_info fieinfo = { 0, };
+ struct inode *inode = filp->f_path.dentry->d_inode;
+ struct super_block *sb = inode->i_sb;
+ u64 len;
+ int error;
+
+ if (!inode->i_op->fiemap)
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&fiemap, (struct fiemap __user *)arg,
+ sizeof(struct fiemap)))
+ return -EFAULT;
+
+ if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS)
+ return -EINVAL;
+
+ error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length,
+ &len);
+ if (error)
+ return error;
+
+ fieinfo.fi_flags = fiemap.fm_flags;
+ fieinfo.fi_extents_max = fiemap.fm_extent_count;
+ fieinfo.fi_extents_start = (struct fiemap_extent *)(arg + sizeof(fiemap));
+
+ if (fiemap.fm_extent_count != 0 &&
+ !access_ok(VERIFY_WRITE, fieinfo.fi_extents_start,
+ fieinfo.fi_extents_max * sizeof(struct fiemap_extent)))
+ return -EFAULT;
+
+ if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC)
+ filemap_write_and_wait(inode->i_mapping);
+
+ error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, len);
+ fiemap.fm_flags = fieinfo.fi_flags;
+ fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped;
+ if (copy_to_user((char *)arg, &fiemap, sizeof(fiemap)))
+ error = -EFAULT;
+
+ return error;
+}
+
static int file_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
{
@@ -80,6 +233,8 @@ static int file_ioctl(struct file *filp, unsigned int cmd,
switch (cmd) {
case FIBMAP:
return ioctl_fibmap(filp, p);
+ case FS_IOC_FIEMAP:
+ return ioctl_fiemap(filp, arg);
case FIGETBSZ:
return put_user(inode->i_sb->s_blocksize, p);
case FIONREAD:
diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h
new file mode 100644
index 0000000..90c2e88
--- /dev/null
+++ b/include/linux/fiemap.h
@@ -0,0 +1,64 @@
+/*
+ * FS_IOC_FIEMAP ioctl infrastructure.
+ *
+ * Some portions copyright (C) 2007 Cluster File Systems, Inc
+ *
+ * Authors: Mark Fasheh <mfasheh-IBi9RG/b67k@public.gmane.org>
+ * Kalpak Shah <kalpak.shah-xsfywfwIY+M@public.gmane.org>
+ * Andreas Dilger <adilger-xsfywfwIY+M@public.gmane.org>
+ */
+
+#ifndef _LINUX_FIEMAP_H
+#define _LINUX_FIEMAP_H
+
+struct fiemap_extent {
+ __u64 fe_logical; /* logical offset in bytes for the start of
+ * the extent from the beginning of the file */
+ __u64 fe_physical; /* physical offset in bytes for the start
+ * of the extent from the beginning of the disk */
+ __u64 fe_length; /* length in bytes for this extent */
+ __u64 fe_reserved64[2];
+ __u32 fe_flags; /* FIEMAP_EXTENT_* flags for this extent */
+ __u32 fe_reserved[3];
+};
+
+struct fiemap {
+ __u64 fm_start; /* logical offset (inclusive) at
+ * which to start mapping (in) */
+ __u64 fm_length; /* logical length of mapping which
+ * userspace wants (in) */
+ __u32 fm_flags; /* FIEMAP_FLAG_* flags for request (in/out) */
+ __u32 fm_mapped_extents;/* number of extents that were mapped (out) */
+ __u32 fm_extent_count; /* size of fm_extents array (in) */
+ __u32 fm_reserved;
+ struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */
+};
+
+#define FIEMAP_MAX_OFFSET (~0ULL)
+
+#define FIEMAP_FLAG_SYNC 0x00000001 /* sync file data before map */
+#define FIEMAP_FLAG_XATTR 0x00000002 /* map extended attribute tree */
+
+#define FIEMAP_FLAGS_COMPAT (FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR)
+
+#define FIEMAP_EXTENT_LAST 0x00000001 /* Last extent in file. */
+#define FIEMAP_EXTENT_UNKNOWN 0x00000002 /* Data location unknown. */
+#define FIEMAP_EXTENT_DELALLOC 0x00000004 /* Location still pending.
+ * Sets EXTENT_UNKNOWN. */
+#define FIEMAP_EXTENT_NO_UNMOUNTED_IO 0x00000008 /* Data can not be read
+ * while fs is unmounted */
+#define FIEMAP_EXTENT_DATA_ENCRYPTED 0x00000080 /* Data is encrypted by fs.
+ * Sets EXTENT_NO_BYPASS. */
+#define FIEMAP_EXTENT_NOT_ALIGNED 0x00000100 /* Extent offsets may not be
+ * block aligned. */
+#define FIEMAP_EXTENT_DATA_INLINE 0x00000200 /* Data mixed with metadata.
+ * Sets EXTENT_NOT_ALIGNED.*/
+#define FIEMAP_EXTENT_DATA_TAIL 0x00000400 /* Multiple files in block.
+ * Sets EXTENT_NOT_ALIGNED.*/
+#define FIEMAP_EXTENT_UNWRITTEN 0x00000800 /* Space allocated, but
+ * no data (i.e. zero). */
+#define FIEMAP_EXTENT_MERGED 0x00001000 /* File does not natively
+ * support extents. Result
+ * merged for efficiency. */
+
+#endif /* _LINUX_FIEMAP_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ae0ab82..0724abf 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -232,6 +232,7 @@ extern int dir_notify_enable;
#define FS_IOC_SETFLAGS _IOW('f', 2, long)
#define FS_IOC_GETVERSION _IOR('v', 1, long)
#define FS_IOC_SETVERSION _IOW('v', 2, long)
+#define FS_IOC_FIEMAP _IOWR('f', 11, struct fiemap)
#define FS_IOC32_GETFLAGS _IOR('f', 1, int)
#define FS_IOC32_SETFLAGS _IOW('f', 2, int)
#define FS_IOC32_GETVERSION _IOR('v', 1, int)
@@ -292,6 +293,7 @@ extern int dir_notify_enable;
#include <linux/mutex.h>
#include <linux/capability.h>
#include <linux/semaphore.h>
+#include <linux/fiemap.h>
#include <asm/atomic.h>
#include <asm/byteorder.h>
@@ -1180,6 +1182,20 @@ extern void dentry_unhash(struct dentry *dentry);
extern int file_permission(struct file *, int);
/*
+ * VFS FS_IOC_FIEMAP helper definitions.
+ */
+struct fiemap_extent_info {
+ unsigned int fi_flags; /* Flags as passed from user */
+ unsigned int fi_extents_mapped; /* Number of mapped extents */
+ unsigned int fi_extents_max; /* Size of fiemap_extent array */
+ struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent
+ * array */
+};
+int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
+ u64 phys, u64 len, u32 flags);
+int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
+
+/*
* File types
*
* NOTE! These match bits 12..15 of stat.st_mode
@@ -1288,6 +1304,8 @@ struct inode_operations {
void (*truncate_range)(struct inode *, loff_t, loff_t);
long (*fallocate)(struct inode *inode, int mode, loff_t offset,
loff_t len);
+ int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
+ u64 len);
};
struct seq_file;
--
To unsubscribe from this list: send the line "unsubscribe linux-api" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 13+ messages in thread
* Re: [PATCH 3/4] generic block based fiemap implementation
2008-10-06 21:14 ` Theodore Tso
@ 2008-10-07 8:14 ` steve
0 siblings, 0 replies; 13+ messages in thread
From: steve @ 2008-10-07 8:14 UTC (permalink / raw)
To: Theodore Tso; +Cc: linux-fsdevel, Josef Bacik, Mark Fasheh
Hi,
On Mon, Oct 06, 2008 at 05:14:02PM -0400, Theodore Tso wrote:
> On Mon, Oct 06, 2008 at 12:35:06PM +0100, steve@chygwyn.com wrote:
> >
> > Would it be possible to move the inode mutex out of generic_block_fiemap()
> > and into the callers? The defined lock ordering in GFS2 is inode mutex ->
> > inode glock, and thus we want to be able to lock in that order. We should
> > be able to use generic_block_fiemap() for GFS2 in that case.
>
> Given that nearly all other block-based filesystems that don't use
> extents would need to take the mutex lock, this would be error-prone.
> What about introducing an _generic_block_fiemap() for use by GFS2 that
> doesn't the inode mutex, and changing generic_block_fiemap() to be a
> wrapper that calls _generic_block_fiemap() and takes the inode mutex
> for the convenience of most other filesystems?
>
Yes, that sounds ok to me.
> This would be a very simple change to make once a patch to enable GFS2
> use of the FIEMAP interface. (If we introduce
> _generic_block_fiemap(), it's likely to get removed by some random
> roving Kernel Janitor, as an exported but unused interface. :-)
>
> It occurs to me though that this is likely not all that is needed for
> GFS2, though, since like Lustre, BTRFS, and ZFS, there can be multiple
> disks or storage devices associated with a single filesystem, correct?
> So we would need to add some way of identifying the disk, not just the
> block number; how does GFS2 identify/enumerate storage devices which
> are part of a particular filesystem?
>
> - Ted
No, we don't need anything else special. So far as GFS2 is concerned
it only uses a single device. If there is a requirement for anything
more complicated, we leave that to lvm etc. I don't know what the
requirements are for the other filesystems you mention in that area.
The original plan was, that if anything complicated was required in terms
of fs layout, then we'd get mkfs to do that at fs create time based on
info which it might query from the underlying device. To date though
we've not implemented anything like that, so its still fairly simple,
Steve.
^ permalink raw reply [flat|nested] 13+ messages in thread
* [PATCH 3/4] generic block based fiemap implementation
2008-10-09 1:48 ` [PATCH 2/4] ocfs2: fiemap support Theodore Ts'o
@ 2008-10-09 1:48 ` Theodore Ts'o
0 siblings, 0 replies; 13+ messages in thread
From: Theodore Ts'o @ 2008-10-09 1:48 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Josef Bacik, Mark Fasheh, Theodore Ts'o
From: Josef Bacik <jbacik@redhat.com>
Any block based fs (this patch includes ext3) just has to declare its own
fiemap() function and then call this generic function with its own
get_block_t. This works well for block based filesystems that will map
multiple contiguous blocks at one time, but will work for filesystems that
only map one block at a time, you will just end up with an "extent" for each
block. One gotcha is this will not play nicely where there is hole+data
after the EOF. This function will assume its hit the end of the data as soon
as it hits a hole after the EOF, so if there is any data past that it will
not pick that up. AFAIK no block based fs does this anyway, but its in the
comments of the function anyway just in case.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: linux-fsdevel@vger.kernel.org
---
fs/ext2/ext2.h | 2 +
fs/ext2/file.c | 1 +
fs/ext2/inode.c | 8 +++
fs/ext3/file.c | 1 +
fs/ext3/inode.c | 8 +++
fs/ioctl.c | 118 +++++++++++++++++++++++++++++++++++++++++++++++
include/linux/ext3_fs.h | 2 +
include/linux/fs.h | 3 +
8 files changed, 143 insertions(+), 0 deletions(-)
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 47d88da..bae998c 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -133,6 +133,8 @@ extern void ext2_truncate (struct inode *);
extern int ext2_setattr (struct dentry *, struct iattr *);
extern void ext2_set_inode_flags(struct inode *inode);
extern void ext2_get_inode_flags(struct ext2_inode_info *);
+extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len);
int __ext2_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata);
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 5f2fa9c..45ed071 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -86,4 +86,5 @@ const struct inode_operations ext2_file_inode_operations = {
#endif
.setattr = ext2_setattr,
.permission = ext2_permission,
+ .fiemap = ext2_fiemap,
};
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 991d6df..7658b33 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -31,6 +31,7 @@
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
+#include <linux/fiemap.h>
#include "ext2.h"
#include "acl.h"
#include "xip.h"
@@ -704,6 +705,13 @@ int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_
}
+int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ return generic_block_fiemap(inode, fieinfo, start, len,
+ ext2_get_block);
+}
+
static int ext2_writepage(struct page *page, struct writeback_control *wbc)
{
return block_write_full_page(page, ext2_get_block, wbc);
diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index acc4913..3be1e06 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -134,5 +134,6 @@ const struct inode_operations ext3_file_inode_operations = {
.removexattr = generic_removexattr,
#endif
.permission = ext3_permission,
+ .fiemap = ext3_fiemap,
};
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 507d868..ebfec4d 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -36,6 +36,7 @@
#include <linux/mpage.h>
#include <linux/uio.h>
#include <linux/bio.h>
+#include <linux/fiemap.h>
#include "xattr.h"
#include "acl.h"
@@ -981,6 +982,13 @@ out:
return ret;
}
+int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ return generic_block_fiemap(inode, fieinfo, start, len,
+ ext3_get_block);
+}
+
/*
* `handle' can be NULL if create is zero
*/
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 045d960..33a6b7e 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -13,6 +13,8 @@
#include <linux/security.h>
#include <linux/module.h>
#include <linux/uaccess.h>
+#include <linux/writeback.h>
+#include <linux/buffer_head.h>
#include <asm/ioctls.h>
@@ -224,6 +226,122 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg)
return error;
}
+#define blk_to_logical(inode, blk) (blk << (inode)->i_blkbits)
+#define logical_to_blk(inode, offset) (offset >> (inode)->i_blkbits);
+
+/*
+ * @inode - the inode to map
+ * @arg - the pointer to userspace where we copy everything to
+ * @get_block - the fs's get_block function
+ *
+ * This does FIEMAP for block based inodes. Basically it will just loop
+ * through get_block until we hit the number of extents we want to map, or we
+ * go past the end of the file and hit a hole.
+ *
+ * If it is possible to have data blocks beyond a hole past @inode->i_size, then
+ * please do not use this function, it will stop at the first unmapped block
+ * beyond i_size
+ */
+int generic_block_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo, u64 start,
+ u64 len, get_block_t *get_block)
+{
+ struct buffer_head tmp;
+ unsigned int start_blk;
+ long long length = 0, map_len = 0;
+ u64 logical = 0, phys = 0, size = 0;
+ u32 flags = FIEMAP_EXTENT_MERGED;
+ int ret = 0;
+
+ if ((ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC)))
+ return ret;
+
+ start_blk = logical_to_blk(inode, start);
+
+ /* guard against change */
+ mutex_lock(&inode->i_mutex);
+
+ length = (long long)min_t(u64, len, i_size_read(inode));
+ map_len = length;
+
+ do {
+ /*
+ * we set b_size to the total size we want so it will map as
+ * many contiguous blocks as possible at once
+ */
+ memset(&tmp, 0, sizeof(struct buffer_head));
+ tmp.b_size = map_len;
+
+ ret = get_block(inode, start_blk, &tmp, 0);
+ if (ret)
+ break;
+
+ /* HOLE */
+ if (!buffer_mapped(&tmp)) {
+ /*
+ * first hole after going past the EOF, this is our
+ * last extent
+ */
+ if (length <= 0) {
+ flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size,
+ flags);
+ break;
+ }
+
+ length -= blk_to_logical(inode, 1);
+
+ /* if we have holes up to/past EOF then we're done */
+ if (length <= 0)
+ break;
+
+ start_blk++;
+ } else {
+ if (length <= 0 && size) {
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size,
+ flags);
+ if (ret)
+ break;
+ }
+
+ logical = blk_to_logical(inode, start_blk);
+ phys = blk_to_logical(inode, tmp.b_blocknr);
+ size = tmp.b_size;
+ flags = FIEMAP_EXTENT_MERGED;
+
+ length -= tmp.b_size;
+ start_blk += logical_to_blk(inode, size);
+
+ /*
+ * if we are past the EOF we need to loop again to see
+ * if there is a hole so we can mark this extent as the
+ * last one, and if not keep mapping things until we
+ * find a hole, or we run out of slots in the extent
+ * array
+ */
+ if (length <= 0)
+ continue;
+
+ ret = fiemap_fill_next_extent(fieinfo, logical, phys,
+ size, flags);
+ if (ret)
+ break;
+ }
+ cond_resched();
+ } while (1);
+
+ mutex_unlock(&inode->i_mutex);
+
+ /* if ret is 1 then we just hit the end of the extent array */
+ if (ret == 1)
+ ret = 0;
+
+ return ret;
+}
+EXPORT_SYMBOL(generic_block_fiemap);
+
static int file_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
{
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 80171ee..8120fa1 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -837,6 +837,8 @@ extern void ext3_truncate (struct inode *);
extern void ext3_set_inode_flags(struct inode *);
extern void ext3_get_inode_flags(struct ext3_inode_info *);
extern void ext3_set_aops(struct inode *inode);
+extern int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len);
/* ioctl.c */
extern int ext3_ioctl (struct inode *, struct file *, unsigned int,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 194fb23..385c9a1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1998,6 +1998,9 @@ extern int vfs_fstat(unsigned int, struct kstat *);
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
unsigned long arg);
+extern int generic_block_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo, u64 start,
+ u64 len, get_block_t *get_block);
extern void get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
--
1.5.6.1.205.ge2c7.dirty
^ permalink raw reply related [flat|nested] 13+ messages in thread
end of thread, other threads:[~2008-10-09 1:48 UTC | newest]
Thread overview: 13+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2008-10-07 1:06 PATCH [0/4] Updated**2 fiemap patches Theodore Ts'o
2008-10-07 1:06 ` [PATCH 1/4] vfs: vfs-level fiemap interface Theodore Ts'o
2008-10-07 1:06 ` [PATCH 2/4] ocfs2: fiemap support Theodore Ts'o
2008-10-07 1:06 ` [PATCH 3/4] generic block based fiemap implementation Theodore Ts'o
2008-10-07 1:06 ` [PATCH 4/4] Hook ext4 to the vfs fiemap interface Theodore Ts'o
[not found] ` <1223341581-13802-2-git-send-email-tytso-3s7WtUTddSA@public.gmane.org>
2008-10-07 1:09 ` [PATCH 1/4] vfs: vfs-level " Theodore Tso
-- strict thread matches above, loose matches on Subject: below --
2008-10-09 1:48 PATCH [0/4] Updated**3 fiemap patches Theodore Ts'o
2008-10-09 1:48 ` [PATCH 1/4] vfs: vfs-level fiemap interface Theodore Ts'o
2008-10-09 1:48 ` [PATCH 2/4] ocfs2: fiemap support Theodore Ts'o
2008-10-09 1:48 ` [PATCH 3/4] generic block based fiemap implementation Theodore Ts'o
2008-10-03 21:59 [PATCH 0/4] Updated fiemap patches Theodore Ts'o
2008-10-03 21:59 ` [PATCH 1/4] vfs: vfs-level fiemap interface Theodore Ts'o
2008-10-03 21:59 ` [PATCH 2/4] ocfs2: fiemap support Theodore Ts'o
2008-10-03 21:59 ` [PATCH 3/4] generic block based fiemap implementation Theodore Ts'o
2008-10-06 11:35 ` steve
2008-10-06 21:14 ` Theodore Tso
2008-10-07 8:14 ` steve
2008-09-13 18:47 YET ANOTHER resend of the fiemap patches Theodore Ts'o
2008-09-13 18:49 ` [PATCH 1/4] vfs: vfs-level fiemap interface Theodore Ts'o
2008-09-13 18:49 ` [PATCH 2/4] ocfs2: fiemap support Theodore Ts'o
2008-09-13 18:49 ` [PATCH 3/4] generic block based fiemap implementation Theodore Ts'o
2008-06-25 22:19 Mark Fasheh
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).